Stereo Vision-Based Convolutional Networks for Object Detection in Driving Environments
| العنوان: | Stereo Vision-Based Convolutional Networks for Object Detection in Driving Environments |
|---|---|
| المؤلفون: | José María Armingol, David Martin, Carlos Guindel |
| المصدر: | Computer Aided Systems Theory – EUROCAST 2017 ISBN: 9783319747262 EUROCAST (2) |
| بيانات النشر: | Springer International Publishing, 2018. |
| سنة النشر: | 2018 |
| مصطلحات موضوعية: | Artificial neural network, Computer science, business.industry, media_common.quotation_subject, Deep learning, 02 engineering and technology, 010501 environmental sciences, 01 natural sciences, Object detection, Stereopsis, Robustness (computer science), Perception, Obstacle avoidance, 0202 electrical engineering, electronic engineering, information engineering, 020201 artificial intelligence & image processing, Computer vision, Artificial intelligence, business, 0105 earth and related environmental sciences, media_common |
| الوصف: | Deep learning has become the predominant paradigm in image recognition nowadays. Perception systems in vehicles can also benefit from the improved features provided by modern neural networks to increase the robustness of critical tasks such as obstacle avoidance. This work proposes a vision-based approach for on-road object detection which incorporates depth information from a stereo vision system within the framework of a state-of-art deep learning algorithm. Experiments performed on the KITTI benchmark show that the proposed approach results in significant improvements in the detection accuracy. |
| ردمك: | 978-3-319-74726-2 |
| URL الوصول: | https://explore.openaire.eu/search/publication?articleId=doi_________::6bf602e290bd1ec16d7988950bd2ef96 https://doi.org/10.1007/978-3-319-74727-9_51 |
| حقوق: | CLOSED |
| رقم الأكسشن: | edsair.doi...........6bf602e290bd1ec16d7988950bd2ef96 |
| قاعدة البيانات: | OpenAIRE |
| ردمك: | 9783319747262 |
|---|