2019/10/07 by Daniel Barry, Barry, Daniel, Munir Shah +7 · 2 citations
Computer Science · Engineering · Mathematics · #Advanced Neural Network Applications #Artificial intelligence #Computer Vision and Pattern Recognition (cs.CV) #Computer hardware #Computer science #Computer vision #Convolutional neural network #Detector #Embedded system #FOS: Computer and information sciences #FOS: Electrical engineering #Human Pose and Action Recognition #Humanoid robot #Image and Video Processing (eess.IV) #Inference #Internet of Things #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Object (grammar) #Object detection #Pattern recognition (psychology) #Raspberry pi #Real-time computing #Robot #Robotics (cs.RO) #Video Surveillance and Tracking Methods #cs.CV #cs.LG #cs.RO #eess.IV #electronic engineering #information engineering #stat.ML
paper · pdf · doi:10.48550/arxiv.1910.03159
6 pages, 5 figures
openalex publication_date 2019/10/07 · arxiv created 2019/10/08 · arxiv updated 2019/10/09 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/05
With the emergence of onboard vision processing for areas such as the internet of things (IoT), edge computing and autonomous robots, there is increasing demand for computationally efficient convolutional neural network (CNN) models to perform real-time object detection on resource constraints hardware devices. Tiny-YOLO is generally considered as one of the faster object detectors for low-end devices and is the basis for our work. Our experiments on this network have shown that Tiny-YOLO can achieve 0.14 frames per second(FPS) on the Raspberry Pi 3 B, which is too slow for soccer playing autonomous humanoid robots detecting goal and ball objects. In this paper we propose an adaptation to the YOLO CNN model named xYOLO, that can achieve object detection at a speed of 9.66 FPS on the Raspberry Pi 3 B. This is achieved by trading an acceptable amount of accuracy, making the network approximately 70 times faster than Tiny-YOLO. Greater inference speed-ups were also achieved on a desktop CPU and GPU. Additionally we contribute an annotated Darknet dataset for goal and ball detection.