TY - GEN
T1 - Smaller Object Detection for Real-Time Embedded Traffic Flow Estimation Using Fish-Eye Cameras
AU - Chen, Ping Yang
AU - Hsieh, Jun Wei
AU - Gochoo, Munkhjargal
AU - Wang, Chien Yao
AU - Liao, Hong Yuan Mark
N1 - Publisher Copyright:
© 2019 IEEE.
PY - 2019/9
Y1 - 2019/9
N2 - Real-time embedded traffic flow estimation (RETFE) systems need accurate and efficient vehicle detection models to meet limited resources in budget, dimension, memory, and computing power. In recent years, object detection became a less challenging task with latest deep CNN-based state-of-the-art models, i.e., RCNN, SSD, and YOLO; however, these models cannot provide desired performance for RETFE systems due to their complex time-consuming architecture. In addition, small object (<30×30 pixels) detection is still a challenging task for existing methods. Thus, we propose a shallow model named Concatenated Feature Pyramid Network (CFPN) that inspired from YOLOv3 to provide above mentioned performance for the smaller object detection. Main contribution is a proposed concatenated block (CB) which has reduced number of convolutional layers and concatenations instead of time-consuming algebraic operations. The superiority of CFPN is confirmed on the COCO and an in-house CarFlow datasets on Nvidia TX2. Thus we conclude that CFPN is useful for real-time embedded smaller object detection task.
AB - Real-time embedded traffic flow estimation (RETFE) systems need accurate and efficient vehicle detection models to meet limited resources in budget, dimension, memory, and computing power. In recent years, object detection became a less challenging task with latest deep CNN-based state-of-the-art models, i.e., RCNN, SSD, and YOLO; however, these models cannot provide desired performance for RETFE systems due to their complex time-consuming architecture. In addition, small object (<30×30 pixels) detection is still a challenging task for existing methods. Thus, we propose a shallow model named Concatenated Feature Pyramid Network (CFPN) that inspired from YOLOv3 to provide above mentioned performance for the smaller object detection. Main contribution is a proposed concatenated block (CB) which has reduced number of convolutional layers and concatenations instead of time-consuming algebraic operations. The superiority of CFPN is confirmed on the COCO and an in-house CarFlow datasets on Nvidia TX2. Thus we conclude that CFPN is useful for real-time embedded smaller object detection task.
KW - Small object detection
KW - YOLOv3
KW - edge computing
KW - fish-eye camera
KW - traffic flow estimation
UR - http://www.scopus.com/inward/record.url?scp=85076800187&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85076800187&partnerID=8YFLogxK
U2 - 10.1109/ICIP.2019.8803719
DO - 10.1109/ICIP.2019.8803719
M3 - Conference contribution
AN - SCOPUS:85076800187
T3 - Proceedings - International Conference on Image Processing, ICIP
SP - 2956
EP - 2960
BT - 2019 IEEE International Conference on Image Processing, ICIP 2019 - Proceedings
PB - IEEE Computer Society
T2 - 26th IEEE International Conference on Image Processing, ICIP 2019
Y2 - 22 September 2019 through 25 September 2019
ER -