DeepCounter: Using Deep Learning to Count Garbage Bags

This paper proposes DeepCounter, an automotive sensing system where deep learning based image processing technology is used to automatically count the number of collected garbage bags from the video taken by a camera mounted on the rear of a garbage truck in order to sense a fine-grain spatio-temporal distribution on the amount of disposed garbage in cities that is envisioned to be helpful to develop novel applications related to garbage collection there. A prototype system is implemented on a GPU-integrated signal-board computer. A detection-tracking-counting (DTC) algorithm is developed and implemented based on the single shot multibox detector (SSD), a well-known real-time object detection algorithm. Experimental evaluation validates the feasibility of the proposed approach using video of realistic garbage collection in Fujisawa city, Japan.

[1]  Takuro Yonezawa,et al.  Road marking blur detection with drive recorder , 2017, 2017 IEEE International Conference on Big Data (Big Data).

[2]  Yin Chen,et al.  An Empirical Study on Coverage-Ensured Automotive Sensing using Door-to-door Garbage Collecting Trucks , 2016, IWSC@Middleware.

[3]  Rong Du,et al.  Effective Urban Traffic Monitoring by Vehicular Sensor Networks , 2015, IEEE Transactions on Vehicular Technology.

[4]  Wei Liu,et al.  SSD: Single Shot MultiBox Detector , 2015, ECCV.

[5]  Raja Sengupta,et al.  Kalman Filter-Based Integration of DGPS and Vehicle Sensors for Localization , 2005, IEEE Transactions on Control Systems Technology.

[6]  Kaiming He,et al.  Focal Loss for Dense Object Detection , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

[7]  Jianguo Zhang,et al.  The PASCAL Visual Object Classes Challenge , 2006 .

[8]  Lothar Thiele,et al.  Revealing the limits of spatio-temporal high-resolution pollution maps , 2013, SenSys '13.

[9]  Andrew Zisserman,et al.  Very Deep Convolutional Networks for Large-Scale Image Recognition , 2014, ICLR.

[10]  Yoshua Bengio,et al.  Understanding the difficulty of training deep feedforward neural networks , 2010, AISTATS.

[11]  Ali Farhadi,et al.  YOLO9000: Better, Faster, Stronger , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[12]  Ryan Newton,et al.  The pothole patrol: using a mobile sensor network for road surface monitoring , 2008, MobiSys '08.

[13]  Ali Farhadi,et al.  You Only Look Once: Unified, Real-Time Object Detection , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[14]  Ali Farhadi,et al.  YOLOv3: An Incremental Improvement , 2018, ArXiv.

[15]  Trevor Darrell,et al.  Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation , 2013, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[16]  Ross B. Girshick,et al.  Fast R-CNN , 2015, 1504.08083.

[17]  Hirozumi Yamaguchi,et al.  Cooperative Vehicle Positioning via V2V Communications and Onboard Sensors , 2011, 2011 IEEE Vehicular Technology Conference (VTC Fall).