首页>
外国专利>
FAST PEDESTRIAN DETECTION METHOD BASED ON AGGREGATION CHANNEL FEATURES
FAST PEDESTRIAN DETECTION METHOD BASED ON AGGREGATION CHANNEL FEATURES
展开▼
机译:基于融合通道特征的快速行人检测方法
展开▼
页面导航
摘要
著录项
相似文献
摘要
Disclosed is a fast pedestrian detection method based on aggregation channel features, which comprises an early-stage position calibration process and a later-stage position screening process. During the early-stage position calibration process, a plurality of pieces of channel feature information in an input video or image are aggregated; an image pyramid of the input image or video in scale space is bui for each scale, an image of each channel feature is calculated; features serving as a pedestrian existing judgement basis are recognized; and the pedestrian position is initially extracted. During the later-stage position screening process, a convolutional neural network classifier is used for further screening each position calibrated in the early stage; and pedestrians appearing in the image or the video are further detected to obtain a detection result. By using the technical solution of the present invention, where a training data amount is large, the classifier can automatically select features with a good recognition ability to serve as a pedestrian judgement basis. The method has good robustness, and also improves the pedestrian detection precision.
展开▼