【摘要】 奶牛行为识别过程中,奶牛目标精准检测是重要前提。一般的奶牛目标检测采用纹理和颜色信息进行识别,对于长时间静止和复杂背景干扰的目标存在目标丢失和检测不精准问题。针对上述问题,文章将图像分割方法和区域面积剔除方法相结合,实现复杂环境下的静止奶牛目标检测。实验结果表明,该方法达到97.4%的识别率。更多还原

【Abstract】 In the process of cow behavior recognition, accurate detection of cow targets is an important prerequisite. Generally,cow target detection uses texture and color information for recognition. For targets that are static for a long time and interfered with complex backgrounds, there are problems of target loss and inaccurate detection. Aiming at the above problems, this paper combines image segmentation method with area removal method to realize the target detection of still cows in complex environments. The experimental results show that the method achieves a recognition rate of 97.4%.更多还原