Areal‐timeclassification and detection method for mutton parts based on single shot multi‐box detector

Abstract

This article proposes a real-time classification and detection method for mutton parts based on a single shot detector (SSD). We acquired 9,000 images of various parts of mutton in a sheep slaughtering workshop, characterized by multiple classes and multiple samples. After image preprocessing, an image dataset of the mutton parts was established for later model training. Subsequently, we introduced transfer learning to train an SSD-VGG network and obtain the optimal model. The optimal model was then applied to determine the category and position of each mutton part in the image, thus realizing the classification and detection of mutton parts. In this method, the average accuracy mAP and average processing time for a single image are selected as the accuracy and speed indicators, respectively, for judging the detection performance of the model. The feature extraction network VGG is replaced with MobileNetV1 to optimize the real-time performance of the SSD. Furthermore, we set an additional illumination dataset with two brightness levels "bright" and "dark" to verify the generalization ability of the optimized model. Finally, four common object detection algorithms, namely YoloV3-MobileNetV1, YoloV3-DarkNet53, Fast-RCNN, and Cascade-RCNN, are introduced to perform comparative experiments on mutton image datasets. The test results prove that the SSD-MobileNetV1 exhibits high accuracy and good real-time performance, with a certain generalization ability. It has a better comprehensive detection ability than other methods and can provide technical support for mutton processing. Practical ApplicationsCurrently, in the processing of mutton, the multiple parts of mutton are identified and sorted manually, which is time-consuming and laborious, and there are certain hidden food safety hazards. A deep-learning-based object detection method can solve the above problems effectively. Therefore, this study uses SSD to perform an accurate real-time recognition of the multiple parts of mutton from its images and provide a visual guidance for mutton sorting robots. It can also aid further research in the slaughtering and processing of other meat.

Research on Automatic Classification and Detection of Mutton Multi-Parts Based on Swin-Transformer

“…Mutton multi-parts, which are the final form of mutton products before marketing, are generally obtained by livestock meat processing enterprises on the basis of different meat cut standards for cutting sheep carcasses. These multi-parts are mainly categorized into two major groups: four-parts and six-parts [ 2 , 3 , 4 ]. Currently, Chinese mutton processing enterprises mainly use semi-automatic processing technology in the mutton multi-part sorting process, where manual sorting and stacking of the multi-part mutton is performed on a conveyor belt.…”

“…Wang et al [ 22 ] developed a sheep carcass segmentation method based on surface convexity by scanning and processing 3D point cloud information. Zhao et al [ 3 ] used YoloV3 to realize accurate recognition of multiple mutton parts; however, the detection accuracy requires further improvement. The aforementioned research methods and results can be used as a reference and explored further to achieve high-precision classification and detection of multiple mutton parts.…”

Lobster Position Estimation Using YOLOv7 for Potential Guidance of FANUC Robotic Arm in American Lobster Processing

“…Various studies have demonstrated the effectiveness of object detection techniques, including YOLO and Faster R-CNN, in tackling challenges across food processing and agriculture sectors. These techniques have been applied to various food items, such as carrots, ham, apples, mutton, fruits, shrimp, Nile tilapia, and Atlantic salmon [5][6][7][8][9][10][11][12].…”