Edge AI Zebra Crossing Detection through Dashcam on the Road
Hardware: reComputer J1020v2 with NVIDIA Jetson Nano
Application: Pedestrian Crossing
Industry: Smart Transportation
Deployment Location: United States
computer vision technology has been successfully deployed in video analytics solutions on the edge, making every camera count on-site. Thus, one more application with vision is the dashcam for situation recognition on the road! For now, it can only do a daily recording of vehicles driving day and night, without any AI analysis to deliver valuable insights to drivers for decision-making in the next step. The edge intelligent device provides a fast and accurate solution based on the YOLO algorithm, effectively identifying zebra crossings and judging whether vehicles cross the line from the perspective of a dashcam.
How it works
The whole system is designed and provided by the team of Zhengde Zhang, Menglu Tan, Zhicai Lan, Haichun Liu, Ling Pei, and WenXian Yu, who proposed the paper “CDNet: a real-time and robust crosswalk detection network on jetson Nano based on YOLOv5” together.
The real-time processing and analysis performance of the Jetson Nano device achieves an impressive 33.1 FPS, furnishing valuable information for drivers. Its high robustness extends to challenging outdoor conditions like rain, snow, cloudy days, or nighttime.
To navigate complex environments, a potent convolutional neural network feature extractor is employed. The network integrates a Sequence-and-Excitation (SE) attention mechanism module for enhanced performance. The Negative Sample Training (NST) method elevates accuracy, and the Region of Interest (ROI) algorithm further accelerates detection speed. The adoption of a novel Slide Receptive Field Short-term Vectors Memory (SSVM) algorithm enhances the precision of vehicle cross-behavior detection. Additionally, a synthetic fog enhancement algorithm is incorporated, enabling the model to adapt seamlessly to foggy conditions.
Seeed NVIDIA Jetson Ecosystem
Seeed is an Elite partner for edge AI in the NVIDIA Partner Network. Explore more carrier boards, full system devices, customization services, use cases, and developer tools on Seeed’s NVIDIA Jetson ecosystem page.
Join the forefront of AI innovation with us! Harness the power of cutting-edge hardware and technology to revolutionize the deployment of machine learning in the real world across industries. Be a part of our mission to provide developers and enterprises with the best ML solutions available. Check out our success case study catalog to discover more edge AI possibilities!
Discover infinite computer vision application possibilities through our vision AI resource hub!
Take the first step and send us an email at edgeai@seeed.cc to become a part of this exciting journey!
Download our latest Jetson product Catalog to find one option that suits you well. If you can’t find the off-the-shelf Jetson hardware solution for your needs, please check out our customization services, and submit a new product inquiry to us at odm@seeed.cc for evaluation.
About Author
