A Modified Object Detection Algorithm Based on SSD

doi:10.3969/j.issn.1006-2475.2020.02.018

Abstract

Abstract: Single Shot MultiBox Detector(SSD), one of the most prevalent object detection algorithms based on deep learning, greatly shortens the time of object detecting, whose accuracy of detection is acceptable. However its accuracy cannot meet the need of practical application. Attention mechanism is helpful in improving the performance of convolutional neural network and the accuracy of detection. This paper modifies SSD with attention mechanism and proposes a modified object detection algorithm based on SSD. The modified SSD has been tested with Pascal VOC dataset. The modified SSD achieves 78.5% mAP in Pascal VOC2007 test set and 77.1% mAP in Pascal VOC2012 test set, which are higher than original SSD 4.2 percentage points and 4.7 percentage points separately.

Key words: object detection, SSD, deep learning, convolutional neural network, attention mechanism

CLC Number:

TP399

SU Meng, LI Wei. A Modified Object Detection Algorithm Based on SSD[J]. Computer and Modernization, 2020, 0(02): 89-.

References

［1］ GIRSHICK R B, DONAHUE J, DARRELL T, et al. Region-based convolutional networks for accurate object detection and segmentation［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2016,38(1):142-158.
［2］ HE K M, ZHANG X Y, REN S Q, et al. Spatial pyramid pooling in deep convolutional networks for visual recognition［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2015,37(9):1904-1916. 〖HJ1.6mm〗
［3］ GIRSHICK R B. Fast R-CNN［C］// International Conference on Computer Vision. 2015:1440-1448.
［4］ REN S Q, HE K M, GIRSHICK R B, et al. Faster R-CNN: Towards real-time object detection with region proposal networks［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017,39(6):1137-1149.
［5］ DAI J F, LI Y, HE K M, et al. R-FCN: Object detection via region-based fully convolutional networks［C］// Proceedings of the 30th International Conference on Neural Information Processing Systems(NIPS’16). 2016:379-387.
［6］〖JP3〗姚群力,胡显,雷宏. 深度卷积神经网络在目标检测中的研究进展［J］. 计算机工程与应用, 2018,54(17):1-9.
［7］ REDMON J, DIVVALA S, GIRSHICK R, et al. You only look once: Unified, real-time object detection［C］// IEEE Conference on Computer Vision and Pattern Recognition. IEEE, 2016:779-788.
［8］ LIU W, ANGUELOV D, ERHAN D, et al. SSD: Single shot multibox detector［C］// European Conference on Computer Vision. Springer, 2016:21-37.
［9］〖JP3〗胡金辰,王雨晨,蒋江红,等. 基于深度卷积网络的目标检测技术综述［J］. 数字技术与应用, 2018,36(4):97-98.
［10］王慧玲,綦小龙,武港山. 基于深度卷积神经网络的目标检测技术的研究进展［J］. 计算机科学, 2018,45(9):11-19.
［11］FU C Y, LIU W, RANGA A, et al. DSSD: Deconvolutional single shot detector［J］. 2017: arXiv:1701.06659.
［12］HE K M, ZHANG X Y, REN S Q, et al. Deep residual learning for image recognition［C］// IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 2016:770-778.
［13］SIMONYAN K, ZISSERMAN A. Very deep convolutional networks for large-scale image recognition［J］. Computer Vision and Pattern Recognition, 2014: arXiv:1409.1556.
［14］JEONG J, PARK H, KWAK N. Enhancement of SSD by concatenating feature maps for object detection［J］. Computer Vision and Pattern Recognition, 2017: arXiv:1705.09587.
［15］BAHDANAU D, CHO K, BENGIO Y. Neural machine translation by jointly learning to align and translate［J］. Computation and Language, 2014: arXiv:1409.0473.
［16］MNIH V, HEESS N, GRAVES A, et al. Recurrent models of visual attention［J］. Machine Learning, 2014:arXiv:1406.6247.
［17］EVERINGHAM M, ESLAMI S M A, GOOL L V, et al. The Pascal visual object classes challenge: A retrospective［J］. International Journal of Computer Vision, 2015,111(1):98-136.
［18］HU J, SHEN L, SUN G, et al. Squeeze-and-excitation networks［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2019: DOI: 10.1109/TPAMI.2019.2913372.

[1]	HE Sida, CHEN Pinghua. Intent-based Lightweight Self-Attention Network for Sequential Recommendation [J]. Computer and Modernization, 2024, 0(12): 1-9.
[2]	ZHAO Chenyang, XUE Tao, LIU Junhua. Fashion Clothing Pattern Generation Based on Improved Stable Diffusion [J]. Computer and Modernization, 2024, 0(12): 15-23.
[3]	HUANG Tingpei1, MA Lubiao1, LI Shibao2, LIU Jianhang1. Gesture Recognition Method Based on WiFi and Prototypical Network [J]. Computer and Modernization, 2024, 0(12): 34-39.
[4]	ZHANG Xiaodong1, BAI Guangzhi1, LI Min1, LI Haoyang2. Oil and Gas Well Production Prediction Model Based on Empirical Wavelet Transform [J]. Computer and Modernization, 2024, 0(12): 53-58.
[5]	LIU Baobao, YANG Jingjing, TAO Lu, WANG Heying . DSMSC Based on Attention Mechanism for Remote Sensing Image Scene Classification [J]. Computer and Modernization, 2024, 0(12): 72-77.
[6]	WANG Yanyuan, MAO Zhengchong. Detection and Recognition Algorithms for Chinese and English Scene Text Images [J]. Computer and Modernization, 2024, 0(12): 84-90.
[7]	LI Junchao1, YOU Fei1, ZHANG Chao2, SU Lele2, GONG Yan2 . BiLSTM-Attention Prediction Model and Error Analysis #br# Based on Novel Multi-objective Coati Optimization Algorithm [J]. Computer and Modernization, 2024, 0(11): 70-76.
[8]	ZHANG Yu1, 2, LI Jing1, 2, MA Ming1, 2, WANG Zhongxiang1, 2, SUN Yan1, 2. YOLOLW: A Novel Lightweight Object Detection Model [J]. Computer and Modernization, 2024, 0(11): 91-98.
[9]	DONG Yuwen. Multi-scale Moving Object Detection Algorithm Based on Improved YOLOv7-tiny [J]. Computer and Modernization, 2024, 0(11): 99-105.
[10]	QI Xian, LIU Daming, CHANG Jiaxin. Multi-view 3D Reconstruction Based on Improved Self-attention Mechanism [J]. Computer and Modernization, 2024, 0(11): 106-112.
[11]	CHEN Kai1, LI Yiting1, 2, QUAN Huafeng1. A River Discarded Bottles Detection Method Based on Improved YOLOv8 [J]. Computer and Modernization, 2024, 0(11): 113-120.
[12]	YANG Jun1, HU Wei1, ZHU Wenfu2. Visual SLAM Loop Closure Detection Algorithm Based on Improved MobileNetV3 [J]. Computer and Modernization, 2024, 0(10): 21-26.
[13]	WEI Xuecheng1, JIANG Lingyun1, LI Yan2, HE Fei2. Improved Roadside Monocular View Small Target Detection Algorithm Based on YOLOv5 [J]. Computer and Modernization, 2024, 0(10): 27-34.
[14]	DU Mengjun1, LI Ang1, TONG Jun1, QIAN Jin1, KANG Kai1, WANG Ruoding1, JIN Wenxing2. Power Information Data Fusion Model Based on Improved Extreme Learning Algorithm [J]. Computer and Modernization, 2024, 0(10): 61-64.
[15]	WANG Yingying, HAO Xiao. Fine-grained Image Classification Based on Res2Net and Recursive Gated Convolution [J]. Computer and Modernization, 2024, 0(10): 74-79.