Alibaba DAMO Academy announced today that it has independently developed an ISP processor for in-vehicle cameras, which allows autonomous vehicles to have better vision at night, thereby improving the safety of autonomous driving.
The technology behind the processor is the 3D noise reduction and image enhancement algorithm developed by the DAMO Academy.
At present, the processor has been used in self-driving logistics vehicles, and the road test performance has reached the industry leading level.
ISP is an important component of the car camera, which is responsible for the arithmetic processing of the signal output by the front-end image sensor CMOS.
Using DAMO Academy's unique 3D noise reduction and image enhancement algorithm, the ISP processor can improve the night image recognition ability of the car camera by more than 10%.
(DAMO Academy's ISP (up) vs industry (bottom))
ISP (Image Signal Processor), that is, an image signal processor, is an important component of a car camera, and its main function is to perform arithmetic processing on the signal output by the front-end image sensor CMOS.
Relying on the ISP processor, the vehicle can use the camera to "see" the scene details.
Alibaba DAMO Academy said that the self-developed ISP processor has greatly improved the image recognition capabilities of car cameras during the day and night.
According to the drive test results of the DAMO Academy Automated Driving Laboratory, using the DAMO Academy ISP processor, the car camera has a significant improvement in image object detection and recognition capabilities by more than 10% compared to the mainstream processor in the night, the most challenging scene , the original obscure labeling can be clearly identified.