Reliable pedestrian detection using a deep neural network trained on pedestrian counts
- Resource Type
- Conference
- Authors
- Ghosh, Sanjukta; Amon, Peter; Hutter, Andreas; Kaup, Andre
- Source
- 2017 IEEE International Conference on Image Processing (ICIP) Image Processing (ICIP), 2017 IEEE International Conference on. :685-689 Sep, 2017
- Subject
- Computing and Processing
Signal Processing and Analysis
Training
Neural networks
Task analysis
Machine learning
Training data
Merging
Feature extraction
Pedestrian Detection
Deep Learning
CNN
Counting Model
Deconvolution
- Language
- ISSN
- 2381-8549
Pedestrian detection is an important task for applications like surveillance, driver assistance systems and autonomous driving. We present a novel approach for detecting pedestrians using a deep convolutional neural network (CNN) trained for counting pedestrians. Our method avoids the need for annotation of the position of the pedestrians in the training data via bounding boxes. The deconvolved outputs of the filters of the trained counting model are used to detect the pedestrians. The average miss rate values on the tested datasets were found to be in the same range as other methods in spite of a simpler training using only pedestrian counts. This method is found to be suitable for detecting pedestrians in crowded scenes with occlusion as well as less crowded scenes.