According to foreign media reports, the MIT Media Lab recently developed a new image sensing system that can recognize the shape and distance of objects in a foggy environment. This image sensing system utilizes 'flight time' Camera technology, this camera technology emits a short laser pulse to an object and then measures the time it takes for the laser to return from the object.
Identifying objects in a foggy driving environment has been one of the major obstacles to the development of autonomous vehicle navigation systems that use visible light. Fog often disperses the laser, making it difficult for autonomous vehicles to recognize the road ahead. However, researchers have developed a This algorithm can find patterns in the scattered light and display obstacle distances.
The researchers tested the system in a simulated dense fog environment. The fog is much denser than the fog encountered by the car in real conditions. Test results show that the system performs much better than human observation, and Most previous imaging systems performed much worse in this environment.
The MIT team will describe their system in a paper published at the International Conference on Computational Photography held in Pittsburgh, Pennsylvania in May this year.