• Industrial Engineering and Management Systems
• /
• 제12권4호
• /
• pp.351-358
• /
• 2013

This paper proposes a multiobjective model describing the trade-offs involved in selecting the locations of drop-off boxes for collecting used products and transporting these products to designated locations. We assume the following reverse flow of used products. Owners of used products (cellular phones, digital cameras, ink cartridges, etc.) take them to the nearest drop-off box when the distance is reasonably short. We also assume that owners living closer to drop-off boxes dispose of more used products than do owners living farther from drop-off boxes. Different types of used products are collected, with each type requiring its own drop-off box. A transportation destination for each product is specified. Three objectives are considered: maximizing the volume of used products collected at drop-off boxes; minimizing the cost of transporting collected products to designated locations; and minimizing the cost of allocating space for drop-off boxes. We formulate the above model as a multiobjective integer programming problem and generate the corresponding set of Pareto optimal solutions. We apply the model to an area using population data for Chofu City, Tokyo, Japan, and analyze the trade-offs between the objectives.

• 한국멀티미디어학회논문지
• /
• 제24권7호
• /
• pp.890-902
• /
• 2021

Although the object detection accuracy with still images has been significantly improved with the advance of deep learning techniques, the object detection problem with video data remains as a challenging problem due to the real-time requirement and accuracy drop with occlusion. In this research, we propose a method in pig detection for video monitoring environment. First, we determine a motion, from a video data obtained from a tilted-down-view camera, based on the average size of each pig at each location with the training data, and extract key frames based on the motion information. For each key frame, we then apply YOLO, which is known to have a superior trade-off between accuracy and execution speed among many deep learning-based object detectors, in order to get pig's bounding boxes. Finally, we merge the bounding boxes between consecutive key frames in order to reduce false positive and negative cases. Based on the experiment results with a video data set obtained from a pig farm, we confirmed that the pigs could be detected with an accuracy of 97% at a processing speed of 37fps.