ROAD: The ROad event Awareness Dataset for Autonomous Driving

TL;DR

The paper introduces the ROAD dataset for autonomous driving, enabling detection and understanding of dynamic road events, and benchmarks various detection algorithms including a new incremental method, to improve situational awareness in autonomous vehicles.

Contribution

It presents the first comprehensive dataset for road event awareness, along with a new incremental detection algorithm and benchmark results for autonomous driving scenarios.

Findings

ROAD dataset enables complex activity detection in autonomous driving.

3D-RetinaNet provides an effective baseline for online road event detection.

State-of-the-art detectors face challenges in real-time situational awareness.

Abstract

Humans drive in a holistic fashion which entails, in particular, understanding dynamic road events and their evolution. Injecting these capabilities in autonomous vehicles can thus take situational awareness and decision making closer to human-level performance. To this purpose, we introduce the ROad event Awareness Dataset (ROAD) for Autonomous Driving, to our knowledge the first of its kind. ROAD is designed to test an autonomous vehicle's ability to detect road events, defined as triplets composed by an active agent, the action(s) it performs and the corresponding scene locations. ROAD comprises videos originally from the Oxford RobotCar Dataset annotated with bounding boxes showing the location in the image plane of each road event. We benchmark various detection tasks, proposing as a baseline a new incremental algorithm for online road event awareness termed 3D-RetinaNet. We also report the performance on the ROAD tasks of Slowfast and YOLOv5 detectors, as well as that of the winners of the ICCV2021 ROAD challenge, which highlight the challenges faced by situation awareness in autonomous driving. ROAD is designed to allow scholars to investigate exciting tasks such as complex (road) activity detection, future event anticipation and continual learning. The dataset is available at https://github.com/gurkirt/road-dataset; the baseline can be found at https://github.com/gurkirt/3D-RetinaNet.