Log In Sign Up

SSA-CNN: Semantic Self-Attention CNN for Pedestrian Detection

by   Chengju Zhou, et al.

Pedestrian detection plays an important role in many applications such as autonomous driving. We propose a method that explores semantic segmentation results as self-attention cues to significantly improve the pedestrian detection performance. Specifically, a multi-task network is designed to jointly learn semantic segmentation and pedestrian detection from image datasets with weak box-wise annotations. The semantic segmentation feature maps are concatenated with corresponding convolution features maps to provide more discriminative features for pedestrian detection and pedestrian classification. By jointly learning segmentation and detection, our proposed pedestrian self-attention mechanism can effectively identify pedestrian regions and suppress backgrounds. In addition, we propose to incorporate semantic attention information from multi-scale layers into deep convolution neural network to boost pedestrian detection. Experiment results show that the proposed method achieves the best detection performance with MR of 6.27 obtain competitive performance on CityPersons dataset while maintaining high computational efficiency.


page 3

page 5


Fusion of Multispectral Data Through Illumination-aware Deep Neural Networks for Pedestrian Detection

Multispectral pedestrian detection has received extensive attention in r...

Illuminating Pedestrians via Simultaneous Detection & Segmentation

Pedestrian detection is a critical problem in computer vision with signi...

Exploring Human Vision Driven Features for Pedestrian Detection

Motivated by the center-surround mechanism in the human visual attention...

What Can Help Pedestrian Detection?

Aggregating extra features has been considered as an effective approach ...

Multispectral Pedestrian Detection via Simultaneous Detection and Segmentation

Multispectral pedestrian detection has attracted increasing attention fr...

Dunhuang murals contour generation network based on convolution and self-attention fusion

Dunhuang murals are a collection of Chinese style and national style, fo...

Pedestrian Detection aided by Deep Learning Semantic Tasks

Deep learning methods have achieved great success in pedestrian detectio...