Multi-Object Detection in Traffic Scenes Based on Improved SSD
Open Access
- 6 November 2018
- journal article
- research article
- Published by MDPI AG in Electronics
- Vol. 7 (11), 302
- https://doi.org/10.3390/electronics7110302
Abstract
In order to solve the problem that, in complex and wide traffic scenes, the accuracy and speed of multi-object detection can hardly be balanced by the existing object detection algorithms that are based on deep learning and big data, we improve the object detection framework SSD (Single Shot Multi-box Detector) and propose a new detection framework AP-SSD (Adaptive Perceive). We design a feature extraction convolution kernel library composed of multi-shape Gabor and color Gabor and then we train and screen the optimal feature extraction convolution kernel to replace the low-level convolution kernel of the original network to improve the detection accuracy. After that, we combine the single image detection framework with convolution long-term and short-term memory networks and by using the Bottle Neck-LSTM memory layer to refine and propagate the feature mapping between frames, we realize the temporal association of network frame-level information, reduce the calculation cost, succeed in tracking and identifying the targets affected by strong interference in video and reduce the missed alarm rate and false alarm rate by adding an adaptive threshold strategy. Moreover, we design a dynamic region amplification network framework to improve the detection and recognition accuracy of low-resolution small objects. Therefore, experiments on the improved AP-SSD show that this new algorithm can achieve better detection results when small objects, multiple objects, cluttered background and large-area occlusion are involved, thus ensuring this algorithm a good engineering application prospect.Keywords
This publication has 22 references indexed in Scilit:
- Improving protein disorder prediction by deep bidirectional long short-term memory recurrent neural networksBioinformatics, 2016
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal NetworksIEEE Transactions on Pattern Analysis and Machine Intelligence, 2016
- Automatic Segmentation of MR Brain Images With a Convolutional Neural NetworkIEEE Transactions on Medical Imaging, 2016
- YFCC100MCommunications of the ACM, 2016
- Deep learningNature Methods, 2015
- Deep learningNature, 2015
- Automated photo‐consistency test for voxel colouring based on fuzzy adaptive hysteresis thresholdingIET Image Processing, 2013
- Vision meets robotics: The KITTI datasetThe International Journal of Robotics Research, 2013
- Adaptation in human visual cortex as a mechanism for rapid discrimination of aversive stimuliNeuroImage, 2007
- Optimization for condition-based maintenance with semi-Markov decision processReliability Engineering & System Safety, 2005