基于环境光检测的场景融合系统

Scene Fusion System Based on Ambient Light Detection

基于深度相机和人眼检测模型实时返回观察者眼睛的位置坐标,利用坐标转换模型计算合理的显示区域,通过颜色传感器的颜色分量数据估计环境色温和亮度;根据提前标定的显示参数映射表调整显示状态,使其最接近环境光的色彩表现。搭建了场景融合实验系统,系统分为位置监测相机、图像采集相机、颜色传感器、显示设备、处理器五部分.分别在色温为6354 K,照度为160 lx的室内场景和色温为6197 K,照度为848 lx的室外场景下进行融合实验.实验结果表明,场景融合方案能够为不同位置的观察者调整显示画面,并根据环境光信息改变显示参数,融合效果优良,单次执行仅需283 ms.

The position coordinates of the observers’eyes were derived in real time based on the depth camera and human eye detection model.Reasonable display area was calculated based on coordinate transformation model.The ambient color temperature and brightness were estimated based on the color component data of the color sensor.Finally,the display state was adjusted to make it nearest to the color performance of ambient light based on the pre-calibrated display parameter mapping table.A scene fusion experimental system was built,which can be divided into five parts:position monitoring camera,image capture camera,color sensor,display device and processor.Fusion experiments were carried out in indoor scenes with color temperature of 6354 K and illumination of 160 lx,and outdoor scenes with color temperature of 6197 K and illumination of 848 lx.The experimental results show that this scene fusion scheme can adjust display area for the observers in different locations,and change display parameters according to ambient light information,then achieve excellent fusion effects.The single execution only takes 283 ms.