【摘要】 在图像多目标实时跟踪系统中,多目标的快速识别是至关重要的.采用多帧相差,将运动目标与静态背景分离;根据图像中亮度不同的区域,采用动态查表法选择阚值,进行二值化;对各个目标提取复杂度、长宽比、紧凑度、复数矩等具有良好不变性的特征;利用神经网络对多目标快速有效的识别.经过实践证明该方法识别准确,速度快,效率高.更多还原

【Abstract】 Target detection and quick recognition is one of the most important steps in an image tracking system. Moving objects can be separated from the background by difference of multi-frame. According to the dynamic threshold table the image was binaried, then invariant characteristics are extracted from every objects. These characteristics can be used for recognition of objects by neural network. The result of computer simulation shows that the method is practical and has high speed in detection and recognition for moving multi-objects.更多还原