RSC-GestureNet: Reliability-Aware Selective Causal Recognition of Chinese Traffic Police Gestures

2026-08-03

AI Summary

This study addresses the robustness challenges of recognizing Chinese traffic police gestures in autonomous driving scenarios, particularly under pose interference and transitional motions. To this end, the authors propose a reliability-aware selective causal inference framework that explicitly models pose confidence as dynamic joint weights within graph-based reasoning. The approach integrates causal temporal aggregation with a selective prediction mechanism to enhance recognition stability. Furthermore, the work introduces CTPGesture-C, the first benchmark dataset encompassing diverse degradation scenarios for comprehensive evaluation. Experimental results demonstrate that the proposed model achieves 93.33% accuracy and 98.80% Early@10 on CTPGesture v1, significantly outperforming existing methods. The framework exhibits superior performance in robustness, early-stage recognition, and cross-degradation generalization.

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.

Problem

• traffic police gestures
• causal recognition
• pose reliability
• robustness
• autonomous driving

Innovation

• reliability-aware recognition
• causal gesture recognition
• pose confidence modeling
• selective inference
• robustness benchmarking