Chapter
Computer Vision and Driving: Problems and Possibilities
03:12 - 16:50 (13:38)
The issue with computer vision and driving is not just about pattern recognition or data but also about physical action, interaction with the environment, and creating safety policies to prevent accidents. AI needs to learn what a human driver learns from experience including safety and ethical concerns, as well as the details of traffic rules and human-road dynamics.
Clips
Despite advances in technology, computer vision remains a challenging field due to the subconscious or unconscious nature of some visual processing.
03:12 - 05:44 (02:32)
Summary
Despite advances in technology, computer vision remains a challenging field due to the subconscious or unconscious nature of some visual processing. A proposal from 1966, the Summer Vision Project, outlined many of the computer vision tasks that are still being worked on today.
ChapterComputer Vision and Driving: Problems and Possibilities
Episode#110 – Jitendra Malik: Computer Vision
PodcastLex Fridman Podcast
The cognitive levels of vision problems can be a challenge.
05:44 - 10:29 (04:44)
Summary
The cognitive levels of vision problems can be a challenge. Computer vision researchers tend to think that the problem is easier than it is, often underestimating the complexity of higher level processing.
ChapterComputer Vision and Driving: Problems and Possibilities
Episode#110 – Jitendra Malik: Computer Vision
PodcastLex Fridman Podcast
The speaker discusses the challenges of developing self-driving cars using computer vision, noting that while deep learning and supervised learning are effective in this field, computer vision systems require significantly more data than humans do to learn the same capabilities.
10:29 - 16:50 (06:21)
Summary
The speaker discusses the challenges of developing self-driving cars using computer vision, noting that while deep learning and supervised learning are effective in this field, computer vision systems require significantly more data than humans do to learn the same capabilities.