Pith. sign in

REVIEW 10 cited by

A Large Scale Event-based Detection Dataset for Automotive

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2001.08499 v3 pith:IXF4C76X submitted 2020-01-23 cs.CV cs.LGcs.ROeess.IV

Pierre de Tournemire , Davide Nitti , Etienne Perot , Davide Migliore , Amos Sironi This is my paper
classification cs.CVcs.LGcs.ROeess.IV
keywords datasetdetectionlargeautomotiveevent-basedrecordingstasksvery
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

We introduce the first very large detection dataset for event cameras. The dataset is composed of more than 39 hours of automotive recordings acquired with a 304x240 ATIS sensor. It contains open roads and very diverse driving scenarios, ranging from urban, highway, suburbs and countryside scenes, as well as different weather and illumination conditions. Manual bounding box annotations of cars and pedestrians contained in the recordings are also provided at a frequency between 1 and 4Hz, yielding more than 255,000 labels in total. We believe that the availability of a labeled dataset of this size will contribute to major advances in event-based vision tasks such as object detection and classification. We also expect benefits in other tasks such as optical flow, structure from motion and tracking, where for example, the large amount of data can be leveraged by self-supervised learning methods.

Discussion (0). Sign in to comment.

Forward citations

Cited by 10 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. DSERT-RoLL: Robust Multi-Modal Perception for Diverse Driving Conditions with Stereo Event-RGB-Thermal Cameras, 4D Radar, and Dual-LiDAR

    cs.CV 2026-04 accept novelty 7.0 of 10

    A multi-sensor driving dataset (stereo event-RGB-thermal, 4D radar, dual LiDAR) under diverse weather and lighting, with 2D/3D benchmarks and a fusion method that improves 3D detection robustness.

  2. Low-latency Event-based Object Detection with Spatially-Sparse Linear Attention

    cs.CV 2026-03 conditional novelty 7.0 of 10

    SSLA-Det is the first fully asynchronous linear-attention detector for event cameras, reaching 0.375 mAP on Gen1 and 0.515 mAP on N-Caltech101 with over 20x lower per-event computation than prior async baselines.

  3. Event Burst Trigger: An Availability Backdoor Attack on Event-Based SNN Object Detection

    cs.CV 2026-07 conditional novelty 6.0 of 10

    Event Burst Trigger poisons training so trigger event bursts force SpikeYOLO to emit dense phantom candidates, inflating NMS latency up to 38× with mAP@0.5 loss below 0.099.

  4. Sensor Generalization for Adaptive Sensing in Event-based Object Detection via Joint Distribution Training

    cs.CV 2026-02 conditional novelty 6.0 of 10

    Varying event-camera sensor parameters during training (thresholds, refractory period, field of view) improves event-based object detection robustness on unseen simulated sensor settings, with modest AP gains across R...

  5. Context-aware Sparse Spatiotemporal Learning for Event-based Vision

    cs.CV 2025-08 conditional novelty 6.0 of 10

    A learned input-adaptive threshold gates neuron activations in event-based neural networks, delivering near-SOTA object detection and optical flow with 32-68% fewer synaptic operations.

  6. Event-based Tiny Object Detection: A Benchmark Dataset and Baseline

    cs.CV 2025-06 conditional novelty 6.0 of 10

    The authors build a large event-level annotated dataset of tiny UAVs and propose a sparse-convolution network with a spatiotemporal correlation loss that reportedly outperforms 13 baseline methods.

  7. WD-DETR: Wavelet Denoising-Enhanced Real-Time Object Detection Transformer for Robot Perception with Event Cameras

    cs.RO 2025-06 conditional novelty 6.0 of 10

    WD-DETR combines a time-decay event representation, wavelet-based denoising in the backbone, and a transformer head to reach new state-of-the-art mAP on DSEC, Gen1, and 1Mpx event camera detection benchmarks.

  8. Event-RGB Adaptive Tracking for Nighttime Highway Perception

    cs.CV 2026-07 conditional novelty 5.5 of 10

    JEAT jointly associates RGB and event detections with NIS-adapted measurement noise, raising MOTA on unlit nighttime highways from 46% (RGB) / 69% (event) to 77% on a new CARLA dataset.

  9. Sequence-SOD: Bio-inspired Sequence-aware Spiking ObjectDetection for Event Cameras

    cs.CV 2026-07 conditional novelty 4.0 of 10

    Sequence-aware SNN training that preserves membrane potentials across multi-label event intervals improves Gen1 detection mAP by about 2–3.5 points over single-interval reset training.

  10. From Ground to Air: Noise Robustness in Vision Transformers and CNNs for Event-Based Vehicle Classification with Potential UAV Applications

    cs.CV 2025-06 reject novelty 4.0 of 10

    On the GEN1 event dataset, a Vision Transformer is reported to be more robust than a ResNet to simulated event noise, while the ResNet is slightly more accurate on clean data.

Pith tools