[1]宫大汉,于龙龙,陈辉,等.面向车规级芯片的对象检测模型优化方法[J].智能系统学报,2021,16(5):900-907.[doi:10.11992/tis.202107057]
GONG Dahan,YU Longlong,CHEN Hui,et al.Object detection model optimization method for car-level chips[J].CAAI Transactions on Intelligent Systems,2021,16(5):900-907.[doi:10.11992/tis.202107057]
点击复制
GONG Dahan,YU Longlong,CHEN Hui,et al.Object detection model optimization method for car-level chips[J].CAAI Transactions on Intelligent Systems,2021,16(5):900-907.[doi:10.11992/tis.202107057]
面向车规级芯片的对象检测模型优化方法
《智能系统学报》[ISSN 1673-4785/CN 23-1538/TP] 卷:
16
期数:
2021年第5期
页码:
900-907
栏目:
吴文俊人工智能科技进步奖一等奖
出版日期:
2021-09-05
- Title:
- Object detection model optimization method for car-level chips
- Keywords:
- artificial intelligence; computer vision; object detection; terminal equipment; car-level chip; convolutional neural network; model acceleration; model quantization
- 分类号:
- TP18
- 摘要:
- 卷积神经网络复杂的网络结构使得模型计算复杂度高，限制了其在自动驾驶等实际终端场景中的应用。针对终端场景下的计算资源受限的问题，本文从轻量化深度模型设计和车规级芯片模型部署验证两方面进行研究。针对深度模型计算效率和检测精度的矛盾，本文设计了基于中心卷积的轻量化对象检测模型，实现功耗低且精度高的模型性能。进一步，本文基于量化感知训练的模型加速部署方法在车规级芯片上开展了系统级部署验证，在车规级芯片tda4上成功实现了高效的对象检测模型，在自动驾驶场景中取得了良好的性能。
- Abstract:
- Convolutional neural networks have achieved great success in visual perception tasks. Its complex network structure makes the model computationally complex, which limits its application in actual terminal scenarios such as autonomous driving. Aiming at the problem of limited computing resources in terminal scenarios, in this paper, we conduct research from two aspects: lightweight deep model design and the model deployment and verification on car-level chips. As for the contradiction between the calculation efficiency of deep models and the detection accuracy, we design a lightweight object detection model based on the center-convolution, enjoying low power consumption and high accuracy model performance. Furthermore, based on the method of quantization aware training, we carried out system-level deployment and verification on car-level chips. We successfully implemented a high-efficiency object detection model on the car-level chips, i.e. tda4, and achieved good performance in autonomous driving scenarios.
- 参考文献/References:
-
[1] REN Shaoqing, HE Kaiming, GIRSHICK R, et al. Faster R-CNN: towards real-time object detection with region proposal networks[C]//Proceedings of Annual Conference on Neural Information Processing Systems 2015. Montreal, Canada, 2015: 91-99.
[2] REDMON J, DIVVALA S, GIRSHICK R, et al. You only look once: unified, real-time object detection[C]//Proceedings of 2016 IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas, USA, 2016: 779?788.
[3] ZHOU Xingyi, WANG Dequan, KR?HENBüHL P. Objects as points[J]. arXiv:1904.07850, 2019.
[4] HE Kaiming, ZHANG Xiangyu, REN Shaoqing, et al. Deep residual learning for image recognition[C]//Proceedings of 2016 IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas, USA, 2016: 770?778.
[5] LAW H, DENG Jia. Cornernet: detecting objects as paired keypoints[C]//Proceedings of the 15th European Conference on Computer Vision. Munich, Germany, 2018: 734-750.
[6] ZHOU Xingyi, ZHUO Jiacheng, KR?HENBüHL P. Bottom-up object detection by grouping extreme and center points[C]//Proceedings of 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Long Beach, USA, 2019: 850?859.
[7] LIU Zili, ZHENG Tu, XU Guodong, et al. Training-time-friendly network for real-time object detection[C]//Proceedings of the Thirty-Fourth AAAI Conference on Artificial Intelligence. New York, USA, 2020: 11685?11692.
[8] ZHOU Xingyi, KOLTUN V, KR?HENBüHL P. Probabilistic two-stage detection[J]. arXiv:2103.07461, 2021.
[9] IOFFE S, SZEGEDY C. Batch normalization: Accelerat-ing deep network training by reducing internal covariate shift[C]//Proceedings of the 32nd International Confer-ence on Machine Learning. Lille, France, 2015: 448-456.
[10] 洪文亮. 基于改进的 Faster R-CNN 的目标检测系统的研究[D]. 长春: 吉林大学, 2019.
HONG Wenliang. Research on systems of object detection based improved Faster R-CNN[D]. Changchun: Jilin University, 2019.
[11] DENG Jia, DONG Wei, SOCHER R, et al. Imagenet: a large-scale hierarchical image database[C]//Proceedings of 2009 IEEE Conference on Computer Vision and Pattern Recognition. Miami, USA, 2009: 248?255.
[12] PASZKE A, GROSS S, MASSA F, et al. PyTorch: an imperative style, high-performance deep learning library[C]//Proceedings of Annual Conference on Neural Information Processing Systems 2019. Vancouver, Canada, 2019: 8026?8037.
[13] ABADI M, BARHAM P, CHEN Jianmin, et al. TensorFlow: a system for large-scale machine learning[C]//Proceedings of the 12th USENIX Symposium on Operating Systems Design and Implementation. Savannah, USA, 2016: 265?283.
[14] KRIZHEVSKY ALEX, SUTSKEVER ILYA, HINTON GEOFFREY E. Imagenet classification with deep convolutional neural networks[C]//Advances in neural information processing systems. Lake Tahoe, USA, 2012, 25: 1097?1105.
[15] KAREN SIMONYAN, ANDREW ZISSERMAN. Very deep convolutional networks for large-scale image re-cognition[EB/OL]. arXiv preprint, 2014. https://arxiv.org/abs/1409.1556.
[16] SZEGEDY C, LIU Wei, JIA Yangqing, et al. Going deeper with convolutions[C]//Proceedings of 2015 IEEE Conference on Computer Vision and Pattern Recognition. Boston, USA, 2015: 1?9.
[17] HUANG Gao, LIU Zhang, LAURENS VAN DER MAATEN, et al. Densely connected convolutional networks[C]//Proceedings of the IEEE conference on computer vision and pattern recognition. Hawaii, USA, 2017: 4700?4708.
[18] HE Kaiming, GKIOXARI G, DOLLáR P, et al. Mask R-CNN[C]//Proceedings of 2017 IEEE International Conference on Computer Vision. Venice, Italy, 2017: 2980?2988.
[19] HUANG Gao, LIU Zhuang, VAN DER MAATEN L, et al. Densely connected convolutional networks[C]//Pro-ceedings of 2017 IEEE Conference on Computer Vision and Pattern Recognition. Honolulu, USA, 2017: 2261-2269.
[20] RONNEBERGER O, FISCHER P, BROX T. U-net: convolutional networks for biomedical image segmentation[C]//Proceedings of the 18th International Conference on Medical Image Computing and Computer-Assisted Inter-vention. Munich, Germany, 2015: 234-241.
[21] 林开颜, 吴军辉, 徐立鸿. 彩色图像分割方法综述[J]. 中国图象图形学报(A 辑), 2005, 10(1): 1?10.
LIN Kaiyan, WU Junhui, XU Lihong. Survey of color image segmentation[J]//Journal of image and araphics(A), 2005, 10(1): 1?10.
[22] ZHENG Liang, YANG Yi, HAUPTMANN A G. Person re-identification: past, present and future[J]. arXiv:1610.02984, 2016.
[23] LUO Hao, GU Youzhi, LIAO Xingyu, et al. Bag of tricks and a strong baseline for deep person re-identification[C]//Proceedings of 2019 IEEE/CVF Conference on Com-puter Vision and Pattern Recognition Workshops. Long Beach, USA, 2019: 1487-1495.
[24] 宋婉茹, 赵晴晴, 陈昌红, 等. 行人重识别研究综述[J]. 智能系统学报, 2017, 12(6): 770–780
SONG Wanru, ZHAO Qingqing, CHEN Changhong, et al. Survey of person reidentification[J]. CAAI transactions on intelligent systems, 2017, 12(6): 770–780
[25] 刘瑞芝, 孙士杰, 王菽裕, 等. 基于三维垂直逆投影面的枚举车速检测算法 [J]. 电子设计工程, 2016, 24(14):165–167.
LIU Ruizhi, SUN Shijie, WANG Shuyu, et al. Enumerated vehicle speed detection algorithm based on three-dimensional vertical back projection surface[J]. Electronic design engineering, 2016, 24(14): 165–167.
- 相似文献/References:
-
[1]李德毅.网络时代人工智能研究与发展[J].智能系统学报,2009,4(1):1.
LI De-yi.AI research and development in the network age[J].CAAI Transactions on Intelligent Systems,2009,4():1.
[2]赵克勤.二元联系数A+Bi的理论基础与基本算法及在人工智能中的应用[J].智能系统学报,2008,3(6):476.
ZHAO Ke-qin.The theoretical basis and basic algorithm of binary connection A+Bi and its application in AI[J].CAAI Transactions on Intelligent Systems,2008,3():476.
[3]徐玉如,庞永杰,甘?? 永,等.智能水下机器人技术展望[J].智能系统学报,2006,1(1):9.
XU Yu-ru,PANG Yong-jie,GAN Yong,et al.AUV—state-of-the-art and prospect[J].CAAI Transactions on Intelligent Systems,2006,1():9.
[4]王志良.人工心理与人工情感[J].智能系统学报,2006,1(1):38.
WANG Zhi-liang.Artificial psychology and artificial emotion[J].CAAI Transactions on Intelligent Systems,2006,1():38.
[5]赵克勤.集对分析的不确定性系统理论在AI中的应用[J].智能系统学报,2006,1(2):16.
ZHAO Ke-qin.The application of uncertainty systems theory of set pair analysis (SPU)in the artificial intelligence[J].CAAI Transactions on Intelligent Systems,2006,1():16.
[6]秦裕林,朱新民,朱? 丹.Herbert Simon在最后几年里的两个研究方向[J].智能系统学报,2006,1(2):11.
QIN Yu-lin,ZHU Xin-min,ZHU Dan.Herbert Simons two research directions in his lost years[J].CAAI Transactions on Intelligent Systems,2006,1():11.
[7]谷文祥,李 丽,李丹丹.规划识别的研究及其应用[J].智能系统学报,2007,2(1):1.
GU Wen-xiang,LI Li,LI Dan-dan.Research and application of plan recognition[J].CAAI Transactions on Intelligent Systems,2007,2():1.
[8]杨春燕,蔡 文.可拓信息-知识-智能形式化体系研究[J].智能系统学报,2007,2(3):8.
YANG Chun-yan,CAI Wen.A formalized system of extension information-knowledge-intelligence[J].CAAI Transactions on Intelligent Systems,2007,2():8.
[9]夏 凡,王 宏.基于局部异常行为检测的欺骗识别研究[J].智能系统学报,2007,2(5):12.
XIA Fan,WANG Hong.Methodologies for deception detection based on abnormal b ehavior[J].CAAI Transactions on Intelligent Systems,2007,2():12.
[10]赵克勤.SPA的同异反系统理论在人工智能研究中的应用[J].智能系统学报,2007,2(5):20.
ZHAO Ke-qin.The application of SPAbased identicaldiscrepancycontrary system theory in artificial intelligence research[J].CAAI Transactions on Intelligent Systems,2007,2():20.
[11]李雪,蒋树强.智能交互的物体识别增量学习技术综述[J].智能系统学报,2017,12(2):140.[doi:10.11992/tis.201701006]
LI Xue,JIANG Shuqiang.Incremental learning and object recognition system based on intelligent HCI: a survey[J].CAAI Transactions on Intelligent Systems,2017,12():140.[doi:10.11992/tis.201701006]
[12]刘彪,黄蓉蓉,林和,等.基于卷积神经网络的盲文音乐识别研究[J].智能系统学报,2019,14(1):186.[doi:10.11992/tis.201805002]
LIU Biao,HUANG Rongrong,LIN He,et al.Research on braille music recognition based on convolutional neural networks[J].CAAI Transactions on Intelligent Systems,2019,14():186.[doi:10.11992/tis.201805002]
[13]王凯诚,鲁华祥,龚国良,等.基于注意力机制的显著性目标检测方法[J].智能系统学报,2020,15(5):956.[doi:10.11992/tis.201903001]
WANG Kaicheng,LU Huaxiang,GONG Guoliang,et al.Salient object detection method based on the attention mechanism[J].CAAI Transactions on Intelligent Systems,2020,15():956.[doi:10.11992/tis.201903001]
[14]宫大汉,陈辉,陈仕江,等.一致性协议匹配的跨模态图像文本检索方法[J].智能系统学报,2021,16(6):1143.[doi:10.11992/tis.202108013]
GONG Dahan,CHEN Hui,CHEN Shijiang,et al.Matching with agreement for cross-modal image-text retrieval[J].CAAI Transactions on Intelligent Systems,2021,16():1143.[doi:10.11992/tis.202108013]
[15]冯晗,姜勇.使用改进Yolov5的变电站绝缘子串检测方法[J].智能系统学报,2023,18(2):325.[doi:10.11992/tis.202201027]
FENG Han,JIANG Yong.A substation insulator string detection method based on an improved Yolov5[J].CAAI Transactions on Intelligent Systems,2023,18():325.[doi:10.11992/tis.202201027]
[16]黄昱程,肖子旺,武丹凤,等.时空融合与判别力增强的孪生网络目标跟踪方法[J].智能系统学报,2024,19(5):1218.[doi:10.11992/tis.202306005]
HUANG Yucheng,XIAO Ziwang,WU Danfeng,et al.Spatiotemporal fusion and discriminative augmentation for improved Siamese tracking[J].CAAI Transactions on Intelligent Systems,2024,19():1218.[doi:10.11992/tis.202306005]
备注/Memo
收稿日期:2021-07-27。
基金项目:国家自然科学基金项目（U1936202，61925107）；中国博士后科学基金创新人才计划项目（BX2021161）
作者简介:宫大汉，博士研究生，主要研究方向为轻量化深度模型结构设计和边缘设备智能推理引擎构建;于龙龙，算法工程师，主要方向为嵌入式智能设备开发和模型部署;丁贵广，副教授，博士，主要研究方向为多媒体信息处理、计算机视觉感知。获国家科技进步二等奖1项、人工智能学会科技进步奖一等奖1项、中国电子学会技术发明一等奖1项。主持和参与重点项目、重点研发项目等国家级项目数十项。发表学术论文近百篇.
通讯作者:丁贵广.E-mail:dinggg@tsinghua.edu.cn
更新日期/Last Update:
1900-01-01