Presents an embedded LPR system with lightweight CNNs achieving 93.6% mAP detection and 87.88% recognition accuracy on the new SL-LPR dataset, running at 11.5 FPS on Xilinx Kria KV260 after Brevitas quantization and FINN FPGA acceleration.
LPYOLO: low precision YOLO for face detection on FPGA,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
An Embedded Real-Time License Plate Recognition System for Complex Traffic Scenes
Presents an embedded LPR system with lightweight CNNs achieving 93.6% mAP detection and 87.88% recognition accuracy on the new SL-LPR dataset, running at 11.5 FPS on Xilinx Kria KV260 after Brevitas quantization and FINN FPGA acceleration.