Commodity shelf segmentation and layer information statistical method based on image detection

The invention relates to the technical field of artificial intelligence, and more particularly relates to a commodity shelf segmentation and layer information statistical method based on image detection. The commodity shelf segmentation and layer information statistical method based on image detection includes training data collection, detection model training and model testing and online use. Sales representatives only need to take pictures of commodity information, shelf division and layer statistical information are processed automatically by a computer, so that labor cost is greatly saved.Staff only needs to take photos, after the photos are transmitted to background, shelf information can be immediately given, so that work efficiency is greatly improved. Statistical information is not restricted by human factors, and accuracy of data is improved. 本发明涉及人工智能的技术领域，更具体地，涉及基于图像检测的商品货架分割和层信息统计方法。基于图像检测的商品货架分割和层信息统计方法，其中，包括训练数据收集、检测模型训练和模型测试及上线使用。销售代表只需要将商品信息图片进行拍摄，货架划分和层数统计信息由电脑自动处理，大大节省了人力成本。工作人员只需要进行拍照，传输到后台