Objective:To improve the defect detection efficiency of the enclosure structure of food storage devices.Methods:A robotic arm inspection trolley based on host computer control was proposed. The acquisition path was planned according to the area of the enclosure structure. The improved Ostu image segmentation method was used to analyze the acquired thermal infrared images and output the "defect" parts. Size and position coordinates, and finally verify the effectiveness of the detection through the defect detection rate and false detection rate.Results: The detection mechanism can completely scan and collect thermal infrared images of the enclosure structure of food storage and transportation devices. The image segmentation method can clearly describe the size of the heat source. The detection rate and false detection rate of "defects" were 92% and 6.6%, respectively.Conclusion: The detection mechanism can completely scan and collect the thermal infrared image of the food storage room envelope, and the image segmentation method can clearly describe the size of the heat source, which meets the practical application requirements of mechanical vision detection.