Illuminating Pedestrians via Simultaneous Detection & Segmentation

Abstract

Pedestrian detection is a critical problem in computer vision with significant impact on safety in urban autonomous driving. In this work, we explore how semantic segmentation can be used to boost pedestrian detection accuracy while having little to no impact on network efficiency. We propose a segmentation infusion network to enable joint supervision on semantic segmentation and pedestrian detection. When placed properly, the additional supervision helps guide features in shared layers to become more sophisticated and helpful for the downstream pedestrian detector. Using this approach, we find weakly annotated boxes to be sufficient for considerable performance gains. We provide an in-depth analysis to demonstrate how shared layers are shaped by the segmentation supervision. In doing so, we show that the resulting feature maps become more semantically meaningful and robust to shape and occlusion. Overall, our simultaneous detection and segmentation framework achieves a considerable gain over the state-of-the-art on the Caltech pedestrian dataset, competitive performance on KITTI, and executes 2x faster than competitive methods.

References in corpus (6)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Caffe: Convolutional Architecture for Fast Feature Embedding
• Going Deeper with Convolutions
• Simultaneous Detection and Segmentation
• Filtered Channel Features for Pedestrian Detection
• Is Faster R-CNN Doing Well for Pedestrian Detection?

Cited by in corpus (7)

• The Adaptability and Challenges of Autonomous Vehicles to Pedestrians in Urban China
• Improving Multispectral Pedestrian Detection by Addressing Modality Imbalance Problems
• GrooMeD-NMS: Grouped Mathematically Differentiable NMS for Monocular 3D Object Detection
• Resisting Crowd Occlusion and Hard Negatives for Pedestrian Detection in the Wild
• Multispectral Fusion for Object Detection with Cyclic Fuse-and-Refine Blocks
• Fully Understanding Generic Objects: Modeling, Segmentation, and Reconstruction
• Partially fake it till you make it: mixing real and fake thermal images for improved object detection