RSC-GestureNet: Reliability-Aware Selective Causal Recognition of Chinese Traffic Police Gestures
2026-08-03 • Computer Vision and Pattern Recognition
Computer Vision and Pattern Recognition
AI summaryⓘ
The authors developed RSC-GestureNet, a system to recognize Chinese traffic police hand signals from video, which is important for self-driving cars to understand. Their method carefully accounts for how reliable the detected body poses are to avoid mistakes, combining information over time and only making predictions when confident. They created a new benchmark to test how well the system handles corrupted or unclear video data. Their approach outperforms previous models in accuracy and early recognition while maintaining stability during gesture transitions. Overall, the study shows that considering pose reliability helps make gesture recognition more robust and precise.
pose estimationgraph convolutional networkscausal inferencegesture recognitiontraffic police signalsreliability modelingtemporal aggregationrobustnessbenchmarkingearly prediction
Authors
Cheng Li, Renjun Gao, Boyi Fu
Abstract
Traffic police gestures are safety-critical perception cues for autonomous driving. A deployable recognizer must infer commands causally from continuous full-frame video, remain stable around transitional arm motion, and avoid over-trusting corrupted pose measurements. This study presents RSC-GestureNet, a reliability-aware selective causal recognizer, for Chinese traffic police gestures. The model treats pose confidence as a first-class signal: unreliable joints are down weighted during graph reasoning, temporal evidence is aggregated causally, and calibrated predictions are selectively emitted through a reliability-aware inference rule. We further introduce CTPGesture-C, a reproducible feature-level corruption benchmark with seven pose/RGB degradation families, and an RGB-level diagnostic in which corrupted frames are reprocessed by MediaPipe before recognition. On the complete official CTPGesture v1 split (134,424 labeled frames and 33,451 causal windows), RSC-GestureNet achieves 93.33+-0.24% accuracy, 91.71+-0.27% macro-F1, 91.69+-0.29% online macro-F1, 98.80+-0.07% Early@10, 0.153+-0.013 s TTC, and the best robust macro-F1 among evaluated methods. Under the same split and causal protocol, it exceeds reproduced traffic-specific MD-GCN and HLP-GCN baselines by 3.23-4.11 macro-F1 points and 2.15-3.07 online-F1 points. These results, together with calibration, selective-risk, statistical, adaptive-branching, and image-level re-extraction analyses, indicate that explicit pose-reliability modeling improves early, stable, and robust traffic-command recognition.