VCANet: Vanishing‑Point‑Guided Context‑Aware Network for Small Road Object Detection

Guang Chen, Kai Chen, Lijun Zhang, Liming Zhang, Alois Knoll

Automotive Innovation, 2021

[Paper]

Abstract

Advanced deep learning technology has made great progress in generic object detection of autonomous driving, yet it is still challenging to detect small road hazards in a long distance owing to lack of large-scale small-object datasets and dedicated methods. This work addresses the challenge from two aspects. Firstly, a self-collected long-distance road object dataset (TJ-LDRO) is introduced, which consists of 109,337 images and is the largest dataset so far for the small road object detection research. Secondly, a vanishing-point-guided context-aware network (VCANet) is proposed, which utilizes the vanishing point prediction block and the context-aware center detection block to obtain semantic information. The multi-scale feature fusion pipeline and the upsampling block in VCANet are introduced to enhance the region of interest (ROI) feature. The experimental results with TJ-LDRO dataset show that the proposed method achieves better performance than the representative generic object detection methods. This work flls a critical capability gap in small road hazards detection for high-speed autonomous vehicles.

Network architecture

TJ-LDRO dataset

You can get our data at Baiduyun Cloud [Download TJ-LDRO], Keywords: v7xm

Qualitative results

Citation

    @article{chen2021vcanet,
      title={VCANet: Vanishing-Point-Guided Context-Aware Network for Small Road Object Detection},
      author={Chen, Guang and Chen, Kai and Zhang, Lijun and Zhang, Liming and Knoll, Alois},
      journal={Automotive Innovation},
      pages={1--13},
      year={2021},
      publisher={Springer}
}