Object detection in real time based on improved single shot multi-box detector algorithm

EURASIP Journal on Wireless Communications and Networking

Zuopeng Justin Zhang¹  Ashwani Kumar²  Hongbo Lyu³ 

[1] Coggin College of Business, University of North Florida, 32224, Jacksonville, FL, USA;Department of Computer Science & Engineering, Vardhaman College of Engineering, Hyderabad, India;Logistics and E-Commerce School, Zhejiang Wanli University, Ningbo, 315100, Zhejiang, China;

关键词: Single shot multi-box detector (SSMB);    Faster region convolutional neural networks (F-CNN);    Loss function;    Aspect ratio;   

DOI  :  10.1186/s13638-020-01826-x

来源: Springer

【 摘 要 】

In today’s scenario, the fastest algorithm which uses a single layer of convolutional network to detect the objects from the image is single shot multi-box detector (SSD) algorithm. This paper studies object detection techniques to detect objects in real time on any device running the proposed model in any environment. In this paper, we have increased the classification accuracy of detecting objects by improving the SSD algorithm while keeping the speed constant. These improvements have been done in their convolutional layers, by using depth-wise separable convolution along with spatial separable convolutions generally called multilayer convolutional neural networks. The proposed method uses these multilayer convolutional neural networks to develop a system model which consists of multilayers to classify the given objects into any of the defined classes. The schemes then use multiple images and detect the objects from these images, labeling them with their respective class label. To speed up the computational performance, the proposed algorithm is applied along with the multilayer convolutional neural network which uses a larger number of default boxes and results in more accurate detection. The accuracy in detecting the objects is checked by different parameters such as loss function, frames per second (FPS), mean average precision (mAP), and aspect ratio. Experimental results confirm that our proposed improved SSD algorithm has high accuracy.

【 授权许可】

CC BY