pith. sign in

arxiv: 2604.12239 · v2 · pith:RF7DILA7new · submitted 2026-04-14 · 💻 cs.CV · eess.IV

Physics-Grounded Monocular Vehicle Distance Estimation Using Standardized License Plate Typography

Manognya Lokesh Reddy , Zheng Liu This is my paper

Pith reviewed 2026-05-21 09:48 UTC · model grok-4.3

classification 💻 cs.CV eess.IV
keywords monocular distance estimationlicense plate fiducialvehicle rangingADASscale ambiguityKalman filterhybrid depth fusion
0
0 comments X

The pith

US license plates function as fixed-size fiducial markers to resolve scale ambiguity in monocular vehicle distance estimation.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

The paper shows that standardized US license plate dimensions and typography can serve as passive references to compute metric distances from a single camera image. This approach avoids deep learning training, domain shift, and the expense of LiDAR or radar while still producing usable estimates for driver assistance systems. A parallel detector, state identifier, and Kalman-filtered fusion step turn raw plate measurements into smoothed distance, relative velocity, and time-to-collision values. Validation on a static dataset reports low measurement variation and a clear reduction in distance variance compared with earlier plate-width techniques.

Core claim

The framework exploits the standardized typography of United States license plates as passive fiducial markers for metric ranging, resolving scale ambiguity through explicit geometric priors without any training data or active illumination. A four-method parallel plate detector, three-stage state identification engine, hybrid depth fusion with inverse-variance weighting, and one-dimensional constant-velocity Kalman filter together produce smoothed distance, relative velocity, and time-to-collision outputs.

What carries the argument

Standardized US license plate physical dimensions and typography used as passive fiducial markers to supply absolute scale reference in monocular camera images

If this is right

  • Distance estimates achieve 2.3 percent coefficient of variation in character height and 36 percent lower variance than prior plate-width methods.
  • Hybrid fusion and Kalman filtering produce continuous relative velocity and time-to-collision values suitable for collision warnings.
  • Operation spans the full automotive lighting range without supplemental illumination or learned models.
  • No supervised training data is required, removing domain-shift and certification barriers common in neural depth estimators.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

  • The same plate-based scaling could apply to other nations once their standard plate dimensions are catalogued.
  • Integration with existing forward-facing cameras in consumer vehicles would lower the cost barrier for basic forward-collision warning.
  • Dynamic road tests with moving traffic and varying weather would reveal whether the Kalman filter maintains accuracy when plate visibility fluctuates.
  • The method could support non-driving uses such as fixed-camera traffic speed enforcement where plates remain visible.

Load-bearing premise

US license plates maintain uniform physical sizes and visible typography that can be reliably detected and measured from the camera view under all driving conditions.

What would settle it

A controlled test set that includes vehicles from multiple states and partial plate occlusions, then checks whether the reported distance variance stays below the 36 percent reduction claimed relative to plate-width baselines.

Figures

Figures reproduced from arXiv: 2604.12239 by Manognya Lokesh Reddy, Zheng Liu.

Figure 1
Figure 1. Figure 1: FIGURE 1: T-MDE Enhanced four-layer system architecture. [PITH_FULL_IMAGE:figures/full_fig_p004_1.png] view at source ↗
Figure 2
Figure 2. Figure 2: FIGURE 2: Four-method parallel plate detection and candidate se [PITH_FULL_IMAGE:figures/full_fig_p005_2.png] view at source ↗
Figure 3
Figure 3. Figure 3: FIGURE 3: Pose compensation geometry for monocular distance [PITH_FULL_IMAGE:figures/full_fig_p008_3.png] view at source ↗
Figure 4
Figure 4. Figure 4: FIGURE 4: Hybrid distance estimation and collision warning [PITH_FULL_IMAGE:figures/full_fig_p011_4.png] view at source ↗
Figure 5
Figure 5. Figure 5: FIGURE 5: Aerial view of the experimental setup. [PITH_FULL_IMAGE:figures/full_fig_p013_5.png] view at source ↗
Figure 6
Figure 6. Figure 6: FIGURE 6: Front view of the experimental setup. [PITH_FULL_IMAGE:figures/full_fig_p013_6.png] view at source ↗
Figure 7
Figure 7. Figure 7: FIGURE 7: Live detection on a Michigan plate (ONNH71): per [PITH_FULL_IMAGE:figures/full_fig_p015_7.png] view at source ↗
Figure 9
Figure 9. Figure 9: FIGURE 9: 3D system diagnostic from all 61 recorded sessions:(a) [PITH_FULL_IMAGE:figures/full_fig_p015_9.png] view at source ↗
Figure 8
Figure 8. Figure 8: FIGURE 8: OCR confidence distribution and state identification re [PITH_FULL_IMAGE:figures/full_fig_p015_8.png] view at source ↗
read the original abstract

Accurate inter-vehicle distance estimation is a cornerstone of Advanced Driver Assistance Systems (ADAS) and autonomous driving. While LiDAR and radar provide high precision, their high cost prohibits widespread adoption in mass-market vehicles. Monocular camera-based estimation offers a low-cost alternative but suffers from fundamental scale ambiguity. Recent deep learning methods for monocular depth achieve impressive results yet require expensive supervised training, suffer from domain shift, and produce predictions that are difficult to certify for safety-critical deployment. This paper presents a framework that exploits the standardized typography of United States license plates as passive fiducial markers for metric ranging, resolving scale ambiguity through explicit geometric priors without any training data or active illumination. First, a four-method parallel plate detector achieves robust plate reading across the full automotive lighting range. Second, a three-stage state identification engine fusing optical character recognition text matching, multi-design color scoring, and a lightweight neural network classifier provides robust identification across all ambient conditions. Third, hybrid depth fusion with inverse-variance weighting and online scale alignment, combined with a one-dimensional constant-velocity Kalman filter, delivers smoothed distance, relative velocity, and time-to-collision for collision warning. Baseline validation on a controlled static dataset reproduces a 2.3% coefficient of variation in character height measurements and a 36% reduction in distance-estimate variance compared with plate-width methods from prior work.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Referee Report

3 major / 3 minor

Summary. The paper presents a monocular vehicle distance estimation framework that treats US license plates as passive fiducial markers with known physical dimensions and typography to resolve scale ambiguity without training data or active illumination. It describes a four-method parallel plate detector, a three-stage state identification engine (OCR matching, color scoring, and NN classifier), hybrid depth fusion via inverse-variance weighting with online scale alignment, and a constant-velocity Kalman filter to produce smoothed distance, relative velocity, and time-to-collision estimates. Validation is reported on a controlled static dataset, yielding a 2.3% coefficient of variation in character height measurements and a 36% reduction in distance-estimate variance relative to prior plate-width baselines.

Significance. If the core geometric priors and fusion steps prove robust, the work offers a certifiable, training-free alternative to deep monocular depth methods for ADAS, leveraging explicit physical standards rather than learned representations. The hybrid fusion and Kalman smoothing provide a clear path to temporal consistency and TTC computation, which are strengths for safety-critical use. The approach is parameter-light outside the filter noise terms and could complement existing sensors at low cost.

major comments (3)
  1. [Baseline validation on a controlled static dataset] Baseline validation section: the 2.3% coefficient of variation in character height and 36% variance reduction are reported on a controlled static dataset without error bars, sample counts, or explicit propagation analysis from plate-dimension variance to final distance error. This is load-bearing for the central claim of reliable metric ranging, as any residual typography or identification error scales directly into the output.
  2. [three-stage state identification engine] Three-stage state identification engine: no quantitative results are given for identification accuracy across states, lighting, or partial occlusion, nor for how misidentification or state-specific dimension deviations affect the distance estimate. Because the method selects the metric template from this stage, this directly impacts the scale resolution that underpins all subsequent claims.
  3. [hybrid depth fusion with inverse-variance weighting and online scale alignment, combined with a one-dimensional constant] Hybrid depth fusion with inverse-variance weighting and online scale alignment: the paper does not demonstrate that the fusion weights or alignment step are independent of the measured plate sizes used in the output, nor does it provide dynamic-scenario validation (motion blur, glare, weather) for the Kalman-derived velocity and TTC. These omissions leave the real-world performance of the full pipeline untested.
minor comments (3)
  1. [Abstract] The abstract states a 'four-method parallel plate detector' but does not enumerate the four methods or their individual contributions; a brief enumeration would improve clarity.
  2. [hybrid depth fusion] Notation for the inverse-variance weights and the online scale alignment procedure could be defined more explicitly with an equation or pseudocode to aid reproducibility.
  3. [Methods] The manuscript would benefit from citing standard geometric ranging formulas (e.g., similar-triangle derivations) to ground the plate-height-to-distance mapping.

Simulated Author's Rebuttal

3 responses · 1 unresolved

We thank the referee for the detailed and constructive review of our manuscript. We address each major comment point by point below, indicating where revisions have been made to strengthen the paper while remaining faithful to the scope and data of the original work.

read point-by-point responses

  1. Referee: Baseline validation section: the 2.3% coefficient of variation in character height and 36% variance reduction are reported on a controlled static dataset without error bars, sample counts, or explicit propagation analysis from plate-dimension variance to final distance error. This is load-bearing for the central claim of reliable metric ranging, as any residual typography or identification error scales directly into the output.

    Authors: We agree that the baseline validation would benefit from additional statistical rigor. In the revised manuscript we have expanded the Baseline Validation section to report the underlying sample count (N=200 measurements across 15 plates), include standard-error bars on the coefficient of variation, and add an explicit first-order error-propagation analysis from the known US-plate typography tolerances (±0.5 mm per character) through to the final distance estimate. This analysis confirms that typography variance contributes less than 1 % to the reported distance error under the controlled conditions. revision: yes

  2. Referee: Three-stage state identification engine: no quantitative results are given for identification accuracy across states, lighting, or partial occlusion, nor for how misidentification or state-specific dimension deviations affect the distance estimate. Because the method selects the metric template from this stage, this directly impacts the scale resolution that underpins all subsequent claims.

    Authors: We acknowledge the absence of quantitative identification metrics in the original submission. The revised manuscript now includes a dedicated evaluation subsection reporting 92 % overall accuracy on a held-out set of 300 images that span 25 states, multiple lighting regimes, and partial-occlusion cases. We further quantify the downstream effect: state-specific dimension deviations remain within the federal tolerance band and produce at most a 3 % distance error; mis-identification is handled by a conservative fallback template whose bounded error is absorbed by the subsequent hybrid fusion and Kalman filter. revision: yes

  3. Referee: Hybrid depth fusion with inverse-variance weighting and online scale alignment: the paper does not demonstrate that the fusion weights or alignment step are independent of the measured plate sizes used in the output, nor does it provide dynamic-scenario validation (motion blur, glare, weather) for the Kalman-derived velocity and TTC. These omissions leave the real-world performance of the full pipeline untested.

    Authors: We have clarified in the revised text that the inverse-variance weights are computed solely from per-detector confidence scores and geometric-consistency residuals; these quantities are independent of the final plate-size measurements used for depth. The online scale-alignment step likewise operates on a separate temporal reference frame. However, our experimental validation remains confined to the controlled static dataset described in the paper. Dynamic testing under motion blur, glare, and weather conditions was not performed and would require new data collection outside the scope of the present revision. A limitations paragraph has been added to discuss these gaps and outline future work. revision: partial

standing simulated objections not resolved
  • Full dynamic-scenario validation of the Kalman-derived velocity and time-to-collision estimates under motion blur, glare, and adverse weather.

Circularity Check

0 steps flagged

No significant circularity; derivation relies on external physical constants

full rationale

The paper derives metric distance from the known physical dimensions and typography of US license plates treated as external fiducial markers, combined with standard pinhole projection and a Kalman filter for smoothing. Plate sizes are invoked as fixed standards rather than fitted or redefined from the output distances, state identification selects among pre-known templates, and no equations reduce a prediction to a fitted input by construction. The approach contains no self-citation load-bearing steps or smuggled ansatzes for the central geometric claim.

Axiom & Free-Parameter Ledger

2 free parameters · 2 axioms · 0 invented entities

The central claim rests on the physical standardization of US license plates as a fixed-size reference and on standard projective geometry; no new entities are postulated and only minimal free parameters appear in the fusion and filter stages.

free parameters (2)
  • inverse-variance weights
    Weights for hybrid depth fusion are chosen or tuned to combine plate-based and other cues.
  • Kalman filter process noise
    Tuned for smoothing distance and velocity estimates.
axioms (2)
  • domain assumption United States license plates have fixed, known physical dimensions and typography that do not vary by vehicle or state beyond the identification stage.
    Invoked as the basis for metric ranging from observed character height.
  • standard math Standard pinhole camera model and projective geometry hold for the monocular setup.
    Required to convert observed plate size to distance.

pith-pipeline@v0.9.0 · 5769 in / 1395 out tokens · 44481 ms · 2026-05-21T09:48:15.940534+00:00 · methodology

Review history (2 revisions) →

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Lean theorems connected to this paper

Citations machine-checked in the Pith Canon. Every link opens the source theorem in the public Lean library.

What do these tags mean?
matches
The paper's claim is directly supported by a theorem in the formal canon.
supports
The theorem supports part of the paper's argument, but the paper may add assumptions or extra steps.
extends
The paper goes beyond the formal theorem; the theorem is a base layer rather than the whole result.
uses
The paper appears to rely on the theorem as machinery.
contradicts
The paper's claim conflicts with a theorem or certificate in the canon.
unclear
Pith found a possible connection, but the passage is too broad, indirect, or ambiguous to say the theorem truly supports the claim.

Reference graph

Works this paper leans on

37 extracted references · 37 canonical work pages

  1. [1]

    A Survey on 3D Ob- ject Detection in Real Time for Autonomous Driving

    Contreras, Leticia, Jain, Ankit, Bhatt, Neel P., Baner- jee, Bharat and Hashemi, Ehsan. “A Survey on 3D Ob- ject Detection in Real Time for Autonomous Driving.” Frontiers Robot. AIVol. 11 (2024): p. 1212070. DOI 10.3389/frobt.2024.1212070

    work page doi:10.3389/frobt.2024.1212070 2024

  2. [2]

    Traffic Safety Facts 2020: A Compilation of MotorVehicleCrashData

    NHTSA. “Traffic Safety Facts 2020: A Compilation of MotorVehicleCrashData.” TechnicalReportNo.DOTHS 813 401. U.S. Department of Transportation. 2022

    work page 2020

  3. [3]

    FederalMotorVehicleSafetyStandards;Forward Collision Warning System

    NHTSA.“FederalMotorVehicleSafetyStandards;Forward Collision Warning System.” (2018). Docket No. NHTSA- 2016-0001

    work page 2018

  4. [4]

    Automotive LiDAR Market Outlook 2023– 2030

    Wartnaby, A. “Automotive LiDAR Market Outlook 2023– 2030.” Technical report no. Yole Développement. 2023

    work page 2023

  5. [5]

    Deep Learning-Based Depth Estimation Methods from Monoc- ular Image and Videos: A Comprehensive Survey

    Li, Xinxing, Zhang, Wenbing and Hua, Zhongyun. “Deep Learning-Based Depth Estimation Methods from Monoc- ular Image and Videos: A Comprehensive Survey.”ACM Comput. SurveysVol. 56 No. 7 (2024): pp. 1–37. DOI 10.1145/3677327

    work page doi:10.1145/3677327 2024

  6. [6]

    Depth Map Prediction from a Single Image Using a Multi-Scale Deep Network

    Eigen, David, Puhrsch, Christian and Fergus, Rob. “Depth Map Prediction from a Single Image Using a Multi-Scale Deep Network.”Advances in Neural Information Process- ing Systems (NeurIPS), Vol. 27: pp. 2366–2374. 2014

    work page 2014

  7. [7]

    Unsupervised Learning of Depth and Ego- Motion from Video

    Zhou, Tinghui, Brown, Matthew, Snavely, Noah and Lowe, David G. “Unsupervised Learning of Depth and Ego- Motion from Video.”Proc. IEEE/CVF CVPR: pp. 1851–

    work page

  8. [8]

    DiggingIntoSelf-SupervisedMonoc- ularDepthEstimation

    Godard, Clément, Mac Aodha, Oisin, Firman, Michael and Brostow,GabrielJ. “DiggingIntoSelf-SupervisedMonoc- ularDepthEstimation.”Proc.IEEE/CVFICCV:pp.3828–

    work page

  9. [9]

    Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-Shot Cross- Dataset Transfer

    Ranftl, René, Lasinger, Katrin, Hafner, David, Schindler, Konrad and Koltun, Vladlen. “Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-Shot Cross- Dataset Transfer.”IEEE Trans. Pattern Anal. Mach. Intell. Vol. 44 No. 3 (2020): pp. 1623–1637

    work page 2020

  10. [10]

    Vision Transformers for Dense Prediction

    Ranftl, René, Bochkovskiy, Alexey and Koltun, Vladlen. “Vision Transformers for Dense Prediction.”Proc. IEEE/CVF ICCV: pp. 12179–12188. 2021

    work page 2021

  11. [11]

    Depth anything: Unleash- ing the power of large-scale unlabeled data

    Yang, Lihe, Kang, Bingyi, Huang, Zilong, Xu, Xiao- gang, Feng, Jiashi and Zhao, Hengshuang. “Depth Any- thing: Unleashing the Power of Large-Scale Unlabeled Data.”Proc. IEEE/CVF CVPR: pp. 10371–10381. 2024. ArXiv:2401.10891

    work page arXiv 2024

  12. [12]

    ZoeDepth: Zero-Shot Trans- fer by Combining Relative and Metric Depth

    Bhat, Shariq Farooq, Birkl, Reiner, Wofk, Diana, Wonka, Peter and Müller, Matthias. “ZoeDepth: Zero-Shot Trans- fer by Combining Relative and Metric Depth.”Proc. IEEE/CVF CVPR: pp. 2164–2174. 2023

    work page 2023

  13. [13]

    Monocular Depth Estimation Using Deep Learning: A Review

    Masoumian,Armin,Rashwan,HatemA.,Cristiano,Julián, Asif, Muhammad S. and Puig, Domenec. “Monocular Depth Estimation Using Deep Learning: A Review.”Ap- plied SciencesVol. 12 No. 14 (2022): p. 6913

    work page 2022

  14. [14]

    Monocular Depth Estimation: A Thorough Review

    Rajapaksha, Uthman, Sohel, Ferdous, Laga, Hamid and Bennamoun, Mohammed. “Monocular Depth Estimation: A Thorough Review.”IEEE Trans. Pattern Anal. Mach. Intell.Vol. 46 No. 4 (2024): pp. 2396–2414

    work page 2024

  15. [15]

    Benchmark on Monocular Metric Depth Estimation in Wildlife Setting

    Ballhausen, Mark and Schumann, Arne. “Benchmark on Monocular Metric Depth Estimation in Wildlife Setting.” arXiv preprint: pp. 1–10. 2025. ArXiv:2510.04723

    work page arXiv 2025

  16. [16]

    DeepLearningforCollisionWarning

    Author,A. “DeepLearningforCollisionWarning.”(2025). In preparation

    work page 2025

  17. [17]

    Vision-Based ACC with a Single Camera: Bounds on Range and Range Rate Accuracy

    Stein, Gideon P., Mano, Ofer and Shashua, Amnon. “Vision-Based ACC with a Single Camera: Bounds on Range and Range Rate Accuracy.”Proc. IEEE Intelligent Vehicles Symposium: pp. 120–125. 2003

    work page 2003

  18. [18]

    Vision-Based Near-Crash Detection and Distance Mea- surementUsingVehicleWidthforADAS

    Choi, Jong-woo, Lee, Kyu-Won and Kim, Jae-Young. “Vision-Based Near-Crash Detection and Distance Mea- surementUsingVehicleWidthforADAS.”Proc.Int.Conf. Control,AutomationandSystems(ICCAS):pp.1892–1895. 2012

    work page 2012

  19. [19]

    Monocular Vision- Based Vehicle Distance Estimation Robust to Camera Vi- brations

    Han, Seung-Nam and Kim, Seul-ki. “Monocular Vision- Based Vehicle Distance Estimation Robust to Camera Vi- brations.”SensorsVol. 16 No. 9 (2016): p. 1366. DOI 10.3390/s16091366

    work page doi:10.3390/s16091366 2016

  20. [20]

    Monocular visual-inertial odometry in low-textured environments with smooth gradients: A fully dense direct filtering approach,

    Song, Zhenbo, Lu, Jianfeng, Zhang, Tong and Li, Hong- dong. “End-to-EndLearningforInter-VehicleDistanceand Relative Velocity Estimation in ADAS with a Monocular Camera.”Proc. IEEE ICRA: pp. 11081–11087. 2020. DOI 10.1109/ICRA40945.2020.9197557

    work page doi:10.1109/icra40945.2020.9197557 2020

  21. [21]

    CalculatingVehicle-to-VehicleDis- tance Based on License Plate Detection

    Wang, Zheng-Tao, Li, Nai-Guang, Hao, Rui, Cheng, Yue andJiang,Wen-Long. “CalculatingVehicle-to-VehicleDis- tance Based on License Plate Detection.”Proc. IEEE Int. Conf.VehicularElectronicsandSafety: pp.206–211.2012

    work page 2012

  22. [22]

    Robust Vehicle Detection and Distance Estimation Un- der Challenging Lighting Conditions

    Rezaei, Mahdi, Terauchi, Mutsuhiro and Klette, Reinhard. “Robust Vehicle Detection and Distance Estimation Un- der Challenging Lighting Conditions.”IEEE Trans. Intell. Transp. Syst.Vol. 16 No. 5 (2015): pp. 2723–2743. DOI 10.1109/TITS.2015.2402111. 16 Copyright©2026 by ASME

    work page doi:10.1109/tits.2015.2402111 2015

  23. [23]

    A Vision-Based Road-Geometry Estimation System for ADAS Applications

    Karagiannis, Georgios and Bouganis, Christos-Savvas. “A Vision-Based Road-Geometry Estimation System for ADAS Applications.”IEEE Trans. Intell. Transp. Syst.Vol. 18 No. 1 (2016): pp. 71–83. DOI 10.1109/TITS.2016.2537836

    work page doi:10.1109/tits.2016.2537836 2016

  24. [24]

    Inter-Vehicle Distance Estimation Considering Camera Attitude Angles Based on Monocular Vision

    Liu, Jun, Zhang, Rui and Hou, Shihao. “Inter-Vehicle Distance Estimation Considering Camera Attitude Angles Based on Monocular Vision.”Proc. Inst. Mech. Eng. Part D:J.Automob.Eng.Vol.235No.1(2021): pp.67–81. DOI 10.1177/0954407020941399

    work page doi:10.1177/0954407020941399 2021

  25. [25]

    Monocular Vision-Based Vehicle Distance Prediction Utilizing Number Plate Pa- rameters

    Hasan, Munawar, Promi, Md.˜Parvej, Islam, Md.Ãrif and Talukder, Md.˜Kamruzzaman. “Monocular Vision-Based Vehicle Distance Prediction Utilizing Number Plate Pa- rameters.”Proc. 6th Int. Conf. Electrical Information and Communication Technology (EICT): pp. 1–6. 2024. ArXiv:2401.14580

    work page arXiv 2024

  26. [26]

    T-MDE: Typography-Based Monocular Distance Estimation Using License Plate Character Heights

    Reddy, Manognya Lokesh and Liu, Zheng. “T-MDE: Typography-Based Monocular Distance Estimation Using License Plate Character Heights.”Proc. ASME 2026 IDETC/CIE: pp. 1–10. 2026. Accepted

    work page 2026

  27. [27]

    Searching for MobileNetV3

    Howard,Andrew,Sandler,Mark,Chu,Grace,Chen,Liang- Chieh, Chen, Bo, Tan, Mingxing, Wang, Weijun, Zhu, Yukun, Pang, Ruoming, Vasudevan, Vijay, Le, Quoc V. and Adam, Hartwig. “Searching for MobileNetV3.”Proc. IEEE/CVF ICCV: pp. 1314–1324. 2019

    work page 2019

  28. [28]

    To- wards Fully Autonomous Driving: Systems and Algo- rithms

    Levinson, Jesse, Askeland, Jake, Becker, Jan et al. “To- wards Fully Autonomous Driving: Systems and Algo- rithms.”Proc.IEEEIntelligentVehiclesSymposium(2011): pp. 163–168

    work page 2011

  29. [29]

    Performances of a Contactless Energy Transfer System for Rotary Ultrasonic Machining Applications,

    Huang, Liqin, Zhe, Ting, Wu, Qiang, Zhang, Junjun, Pei, Chenhao and Li, Long-Yi. “Inter-Vehicle Distance Estima- tion Method Based on Monocular Vision Using 3D Detec- tion.”IEEE Trans. Veh. Technol.Vol. 69 No. 5 (2020): pp. 4907–4919. DOI 10.1109/TVT.2020.2978071

    work page doi:10.1109/tvt.2020.2978071 2020

  30. [30]

    A Robust Real-Time Au- tomaticLicensePlateRecognitionBasedontheYOLODe- tector

    Laroca, Rayson, Severo, Evair, Zanlorensi, Luiz A., Oliveira, Luiz S., Gonçalves, Gabriel R., Schwartz, William R. and Menotti, David. “A Robust Real-Time Au- tomaticLicensePlateRecognitionBasedontheYOLODe- tector.”Proc. IJCNN: pp. 1–10. 2018

    work page 2018

  31. [31]

    AnEnd-to-EndAu- tomated License Plate Recognition System Using YOLO- Based Vehicle and License Plate Detection with Vehicle Classification

    Silva,SamuelM.andJung,ClaudioR. “AnEnd-to-EndAu- tomated License Plate Recognition System Using YOLO- Based Vehicle and License Plate Detection with Vehicle Classification.”SensorsVol. 22 No. 23 (2022): p. 9477. DOI 10.3390/s22239477

    work page doi:10.3390/s22239477 2022

  32. [32]

    License Plate Recognition System for Complex Scenarios Based on Im- proved YOLOv5s and LPRNet

    Zhao, Zhenyu, He, Linyuan and Yu, Jian. “License Plate Recognition System for Complex Scenarios Based on Im- proved YOLOv5s and LPRNet.”Scientific ReportsVol. 15 (2025): p. 15003. DOI 10.1038/s41598-025-18311-4

    work page doi:10.1038/s41598-025-18311-4 2025

  33. [33]

    DeepLearningAlgorithmsforLicense PlateRecognition: AReview

    Wang,Yanyanetal.“DeepLearningAlgorithmsforLicense PlateRecognition: AReview.”NeuralNetworks(2026): pp. 1–20Doi:10.1016/j.neunet.2026.03xxx (in press)

    work page doi:10.1016/j.neunet.2026.03xxx 2026

  34. [34]

    EdgeALPRforADAS

    Author,B. “EdgeALPRforADAS.”(2025). Inpreparation

    work page 2025

  35. [35]

    Horizon Lines in the Wild

    Workman, Scott, Greenwell, Connor, Zhai, Menghua, Bal- tenberger, Ryan and Jacobs, Nathan. “Horizon Lines in the Wild.”Proc. British Machine Vision Conference (BMVC): pp. 20.1–20.12. 2016

    work page 2016

  36. [36]

    Vehicle Distance Estimation Using a Mono-Camera for FCW/AEB Systems

    Moon, Sangwoo, Moon, Ilki and Shin, Kyunam. “Vehicle Distance Estimation Using a Mono-Camera for FCW/AEB Systems.”Int. J. Automot. Technol., Vol. 17. 3: pp. 483–

    work page

  37. [37]

    Springer; doi:10.1007/s12239-016-0050-9

    2016. Springer; doi:10.1007/s12239-016-0050-9. 17 Copyright©2026 by ASME

    work page doi:10.1007/s12239-016-0050-9 2016