STRIDE: Street View-based Environmental Feature Detection and Pedestrian Collision Prediction

Abstract

This paper introduces a novel benchmark to study the impact and relationship of built environment elements on pedestrian collision prediction, intending to enhance environmental awareness in autonomous driving systems to prevent pedestrian injuries actively. We introduce a built environment detection task in large-scale panoramic images and a detection-based pedestrian collision frequency prediction task. We propose a baseline method that incorporates a collision prediction module into a state-of-the-art detection model to tackle both tasks simultaneously. Our experiments demonstrate a significant correlation between object detection of built environment elements and pedestrian collision frequency prediction. Our results are a stepping stone towards understanding the interdependencies between built environment conditions and pedestrian safety.

References in corpus (12)

• DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detection
• The ApolloScape Open Dataset for Autonomous Driving and its Application
• The EuroCity Persons Dataset: A Novel Benchmark for Object Detection
• Accident Risk Prediction based on Heterogeneous Sparse Data: New Dataset and Insights
• Restricted Deformable Convolution based Road Scene Semantic Segmentation Using Surround View Cameras
• Computer Vision-based Accident Detection in Traffic Surveillance
• Real-Time Accident Detection in Traffic Surveillance Using Deep Learning
• A Countrywide Traffic Accident Dataset
• When, Where, and What? A New Dataset for Anomaly Detection in Driving Videos
• Simultaneous multi-view instance detection with learned geometric soft-constraints
• TAD: A Large-Scale Benchmark for Traffic Accidents Detection from Video Surveillance
• COLLIDE-PRED: Prediction of On-Road Collision From Surveillance Videos