Fast Human Head and Shoulder Detection Using Convolutional Networks and RGBD Data
Authors:
- 1 June 2020
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 479-487
Abstract
We introduce a new real-time approach for human head and shoulder detection from RGB-D data based on a combination of image processing and deep learning approaches. Candidate head-top locations (CHL) are generated from a fast and accurate image processing algorithm that operates on depth data. We propose enhancements to the CHL algorithm making it three times faster. Various deep learning models are then evaluated for the tasks of classification and detection on the candidate head-top locations to regress the head bounding boxes and detect shoulder keypoints. We propose three different models based on convolutional neural networks for this problem. Experimental results for different architectures of our model are discussed. We also compare the performance of our models to other state of the art methods in terms of accuracy of detections and computational cost and show that our proposed models are on par with the state of the art in terms of precision-recall of head detection and precision of shoulders detection, with the biggest advantage of our models being in terms of computation time. We also analyze the effect of adding the depth channel on the performance of the network.Keywords
This publication has 17 references indexed in Scilit:
- In-Vehicle Occupancy Detection With Convolutional Networks on Thermal Images2019
- Efficient and robust Pedestrian Detection using Deep Learning for Human-Aware NavigationRobotics and Autonomous Systems, 2019
- 2D/3D Pose Estimation and Action Recognition Using Multitask Deep Learning2018
- Realtime Multi-person 2D Pose Estimation Using Part Affinity Fields2017
- People counting based on head detection combining Adaboost and CNN in crowded surveillance environmentNeurocomputing, 2016
- Rethinking the Inception Architecture for Computer Vision2016
- 2D Human Pose Estimation: New Benchmark and State of the Art Analysis2014
- Real-time human detection and tracking in complex environments using single RGBD camera2013
- Selective Search for Object RecognitionInternational Journal of Computer Vision, 2013
- Support-vector networksMachine Learning, 1995