3D depth camera for face recognition of automobiles

Original 3d camera can only measure the distance simply, mainly used for the focusing of the mobile phone camera. With the expansion of the pixel array, the 3d depth camera appears. At present, 3d depth camera has two main purposes in mobile phones: one is for face recognition and payment in the front; the other is for depth imaging and AR images in the rear.
3d depth camera is applied to hand smartphones, and is also used in automobiles. It is used in three fields. One is driver fatigue monitoring, gesture recognition, and face recognition inside the cockpit; the second field is solid-state lidar, 3d depth camera. It can be seen as a solid-state lidar; the third field is the field of automatic parking.
Compared with the traditional single-camera fatigue driving monitoring, the 3d depth camera has many advantages. It not only has all the functions of the traditional camera, but also has head posture and line of sight analysis. The pure camera requires complex deep learning algorithms, a large amount of data collection, huge software development costs, and consumes a lot of GPU computing resources, which requires corresponding high hardware costs. Even so, the real-time performance is nowhere near as good as a 3d depth camera. Compared with structured light, the robustness is greatly improved, especially at night, when the light changes sharply from opposite car lights and street lights, the structured light is severely disturbed, and the 3D depth camera is hardly disturbed.

Categorized as Blog