449 results about "Mobile camera" patented technology

The invention discloses a mobile phone dynamic camera flash lamp luminance compensation system and a method. The mobile phone dynamic camera flash lamp luminance compensation system and the method comprise the following steps: step A, a mobile phone camera is started and a distance detection unit and a luminance detection unit are started at the same time; step B, the distance between a mobile phone and a scene is acquired through the distance detection unit, the luminance of the scene is acquired through the luminance detection unit at the same time, and the acquired distance value and the acquired luminance value are reported back to a central proceeding unit (CPU); step C, the CPU correspondingly calls a dynamic luminance compensation database in a storer according to the distance value and the luminance value, and acquires flash lamp luminance compensation data at the current distance and the current luminance; and step D, the CPU controls a flash lamp to conduct luminance compensation processing on the photographed scene according to the acquired flash lamp luminance compensation data. According to the mobile phone dynamic camera flash lamp luminance compensation system and the method, the distance and the luminance of the photographed scene are detected through the distance detection unit and the luminance detection unit, wherein the distance detection unit and the luminance detection unit are installed at an end where the camera is located, the dynamic luminance compensation database is called to compensate the flash lamp luminance of the current photographed scene, so that optimal photographing effects of the photographed scene can be achieved, the problem that the flash lamp luminance compensation is not accurate when a mobile phone camera is used for taking photos at present is solved, and photographing effects of the mobile phone camera are improved.

The invention discloses a deep learning pedestrian detection method based on an embedded terminal. The method comprises the steps that first, at a sample preparation stage, an existing automatic driving dataset is acquired, or manual annotations obtained after a fixed camera and a mobile camera shoot videos are collected; second, at a training stage, a large quantity of training images are used totrain parameters of a constructed convolutional neural network so as to complete detection feature learning; third, at a test stage, a large quantity of test images are input into the trained convolutional neural network, and a detection result is obtained; and fourth, at a porting stage, code level optimization and porting into the embedded terminal are performed. According to the method, the 18-layer convolutional neural network is adopted to perform pedestrian feature learning, and the method has an innovative advantage compared with a traditional machine learning method; and an optimization strategy for the embedded terminal is also proposed, the network scale and algorithm complexity are further reduced, and the method is suitable for ADAS function application.

A system, device and method for conducting surveillance of activities, which is configured to autonomously capture of video of a scene being experienced by an individual, the device being configured to be supported on a user. The device includes components that capture and transmit video, and is configured to operate in a plurality of modes, including one mode where the device relays streaming video and at least one other mode or period mode where the device transmits a frame of a video image at a predetermined time interval. The device is configured to autonomously switch from one mode, such as, the period mode, to a live streaming mode of operation upon actuation based on a condition of a user or the user's environment. Embodiments of the device may be configured with a removable capture accessory that provides alternate scene viewing or recording options.