摘要
提出了一种基于深度学习的车位智能检测方法。利用TensorFlow深度学习平台对车辆目标识别模型进行了训练,提取了有效车辆图像的优化间隔,给出了车辆分布的精准识别结果,实现了对车辆分布识别结果的有序编号和车位空缺状况的准确判断。利用模拟数据和实际采集数据,分别验证了车位分布的智能识别、车位智能编号和空车位判断的可靠性。
Based on deep learning, one method for the intelligent detection of parking spaces is proposed. The TensorFlow deep learning platform is applied to train the car object recognition model, the optimal interval of the effective car images is extracted, the accurate recognition result of the car distribution is presented, and the order numbering of the recognition results of the car distribution and the accurate judgment of the vacancy situation of parking spaces are realized. The simulation results and the actually collected data are adopted to verify the reliability of intelligent identification of parking space distribution, intelligent numbering of parking space, and the judgement of empty parking space.
引文
[1] True N.Vacant parking space detection in static images[D].San Diego:University of California,2007:17.
[2] Bong D B L,Ting K C,Lai K C.Integrated approach in the design of car park occupancy information system (COINS)[J].IAENG International Journal of Computer Science,2008,35:1.
[3] Ichihashi H,Notsu A,Honda K,et al.Vacant parking space detector for outdoor parking lot by using surveillance camera and FCM classifier[C].2009 IEEE International Conference on Fuzzy Systems,2009:127-134.
[4] Almeida P,Oliveira L S,Silva E,et al.Parking space detection using textural descriptors[C].2013 IEEE International Conference on Systems,Man,and Cybernetics,2013:3603-3608.
[5] Rahtu E,Heikkil? J,Ojansivu V,et al.Local phase quantization for blur-insensitive image analysis[J].Image and Vision Computing,2012,30(8):501-512.
[6] Shaaban K,Tounsi H.Parking space detection system using video images[J].Transportation Research Record:Journal of the Transportation Research Board,2015,2537:137-147.
[7] Karakaya M,Ak?nc? F C.Parking space occupancy detection using deep learning methods[C].2018 26th Signal Processing and Communications Applications Conference (SIU),2018:1-4.
[8] Jiang D L,Deng H L,Ping Y,et al.Parking cell detection algorithms of multiple characteristics based on video image[J].Journal of Beijing University of Technology,2008,34(2):137-140.蒋大林,邓红丽,平彧,等.基于视频图像的多特征车位检测算法[J].北京工业大学学报,2008,34(2):137-140.
[9] Ye Q,Xu J M,Lin P Q.Parking space occupancy detection based on computer vision[J].Journal of Transport Information and Safety,2014,32(6):39-43.叶卿,徐建闽,林培群.基于计算机视觉的停车位车辆存在性检测方法[J].交通信息与安全,2014,32(6):39-43.
[10] Ding Y Z,Luo X Q,Yang M H,et al.Design and development on remote video surveillance system of parking space[J].Electronic Measurement Technology,2015,38(3):35-38,42.丁元舟,罗小巧,杨明红,等.停车场远程视频监控系统的设计与开发[J].电子测量技术,2015,38(3):35-38,42.
[11] An X X,Deng H M,Shi X Y.Parking lot space detection method based on mini convolutional neural network[J].Journal of Computer Applications,2018,38(4):935-938.安旭骁,邓洪敏,史兴宇.基于迷你卷积神经网络的停车场空车位检测方法[J].计算机应用,2018,38(4):935-938.
[12] Zheng Z Y,Gu S Y.TensorFlow:combat Google deep learning framework[M].Beijing:Electronics Industry Press,2017:10-13.郑泽宇,顾思宇.TensorFlow:实战Google深度学习框架[M].北京:电子工业出版社,2017:10-13.
[13] Ren S Q,He K M,Girshick R,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.
[14] Dai J,Li Y,He K,et al.R-FCN:Object detection via region-based fully convolutional networks[C].30th Conference in Neural Information Processing Systems (NIPS 2016),2016.
[15] Liu W,Anguelov D,Erhan D,et al.SSD:single shot multibox detector[M].Liu W,Anguelov D,Erhan D,et al.eds.Computer Vision-ECCV 2016.Cham:Springer International Publishing,2016:21-37.
[16] Simonyan K,Zisserman A.Very deep convolutional networks for large-scale image recognition[C].IEEE Conference on Computer Vision and Pattern Recognition (CVPR),2014.
[17] Zhao H,An W S.Image salient object detection combined with deep learning[J].Laser and Optoelectronics Progress,2018,55(12):121003.赵恒,安维胜.结合深度学习的图像显著目标检测[J].激光与光电子学进展,2018,55(12):121003.
[18] 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.
[19] Szegedy C,Liu W,Jia Y Q,et al.Going deeper with convolutions[C].IEEE Conference on Computer Vision and Pattern Recognition (CVPR),2015:1-9.
[20] Ioffe S,Szegedy C.Batch normalization:Accelerating deep network training by reducing internal covariate shift[C].IEEE Conference on Learning,2015.
[21] Szegedy C,Vanhoucke V,Ioffe S,et al.Rethinking the inception architecture for computer vision[C].IEEE Conference on Computer Vision and Pattern Recognition (CVPR),2016:2818-2826.
[22] Szegedy C,Ioffe S,Vanhoucke V,et al.Inception-v4,inception-resnet and the impact of residual connections on learning[C].Proceedings of the Third-First AAAI Conference on Artificial Intelligence (AAAI-17),2017:4278-4284.
[23] Howard A G,Zhu M,Chen B,et al.Mobilenets:Efficient convolutional neural networks for mobile vision applications[C].IEEE Conference on Computer Vision and Pattern Recognition (CVPR),2017.
[24] Huang J,Rathod V,Sun C,et al.Speed/Accuracy trade-offs for modern convolutional object detectors[C].IEEE Conference on Computer Vision and Pattern Recognition (CVPR),2017:3296-3297.
[25] Ioffe S,Szegedy C.Batch normalization:Accelerating deep network training by reducing internal covariate shift[C].Proceedings of the 32nd International Conference on Machine Learning,2015,37:448-456.