Object Detection in RGB-D Image Based on ANNet

Authors

Cai Qiang, Beijing Key Laboratory of Big Data Technology for Food Safety, School of Computer and Information Engineering, Beijing Technology and Business University, Beijing 100048, China;
Liwei Wei, Beijing Key Laboratory of Big Data Technology for Food Safety, School of Computer and Information Engineering, Beijing Technology and Business University, Beijing 100048, China;
Haisheng Li, Beijing Key Laboratory of Big Data Technology for Food Safety, School of Computer and Information Engineering, Beijing Technology and Business University, Beijing 100048, China;
Cao Jian, Beijing Key Laboratory of Big Data Technology for Food Safety, School of Computer and Information Engineering, Beijing Technology and Business University, Beijing 100048, China;

Abstract

Abstract: The wide spread of depth images acquisition devices makes object detection in RGB-D images a hotspot in the field of computer vision. In order to make the features extracted by CNN more robust and to improve the detection accuracy, an improved CNN called ANNet was designed. To enhance the model discriminability of local patches within the receptive field, some linear convolutional layers in the AlexNet with nonlinear convolutional layers were replaced which contained multilayer perceptron against the linear feature between convolution filter and underlying data patch. The experiment result shows that the detection accuracy is improved by 3% in the RGB images and 4% in the RGB-D images on the NYUD2 datasets using the improved network.

Recommended Citation

Qiang, Cai; Wei, Liwei; Li, Haisheng; and Jian, Cao (2020) "Object Detection in RGB-D Image Based on ANNet," Journal of System Simulation: Vol. 28: Iss. 9, Article 48.
Available at: https://dc-china-simulation.researchcommons.org/journal/vol28/iss9/48

First Page

2260

Revised Date

2016-07-11

DOI Link

https://doi.org/

Last Page

2266

CLC

TP391

Recommended Citation

Cai Qiang, Wei Liwei, Li Haisheng, Cao Jian. Object Detection in RGB-D Image Based on ANNet[J]. Journal of System Simulation, 2016, 28(9): 2260-2266.