• Journal of Korea Society of Digital Industry and Information Management
• /
• v.18 no.4
• /
• pp.31-40
• /
• 2022

YOLOv4 can be used for detecting parking vehicles in order to check a vehicle in out-door parking space. YOLOv4 has 9 anchor boxes in each of 13x13 grid cells for detecting a bounding box of object. Because anchor boxes are allocated based on each cell, there can be existed small observational error for detecting real objects due to the distance between neighboring cells. In this paper, we proposed YOLOv4 grid cell shift algorithm for improving the out-door parking vehicle detection accuracy. In order to get more chance for trying to object detection by reducing the errors between anchor boxes and real objects, grid cells over image can be shifted to vertical, horizontal or diagonal directions after YOLOv4 basic detection process. The experimental results show that a combined algorithm of a custom trained YOLOv4 and a cell shift algorithm has 96.6% detection accuracy compare to 94.6% of a custom trained YOLOv4 only for out door parking vehicle images.

• Animal Systematics, Evolution and Diversity
• /
• v.40 no.4
• /
• pp.266-275
• /
• 2024

Parrots, especially the Cacatua species, are a particular focus for trade because of their mimicry, plumage, and intelligence. Indeed, Cacatua species are imported most into Korea. To manage trade in wildlife, it is essential to identify the traded species. This is conventionally achieved by morphological identification by experts, but the increasing volume of trade is overwhelming them. Identification of parrots, particularly Cacatua species, is difficult due to their similar features, leading to frequent misidentification. There is thus a need for tools to assist experts in accurately identifying Cacatua species in situ. Deep learning-based object detection models, such as the You Only Look Once (YOLO) series, have been successfully employed to classify wildlife and can help experts by reducing their workloads. Among these models, YOLO versions 5 and 8 have been widely applied for wildlife classification. The later model normally performs better, but selecting and designing a suitable model remains crucial for custom datasets, such as wildlife. Here, YOLO versions 5 and 8 were employed to classify 13 Cacatua species in the image data. Images of these species were collected from eBird, iNaturalist, and Google. The dataset was divided, with 80% used for training and validation and 20% for evaluating model performance. Model performance was measured by mean average precision, with YOLOv5 achieving 0.889 and YOLOv8 achieving 0.919. YOLOv8 was thus better than YOLOv5 at detecting and classifying Cacatua species in the examined images. The model developed here could significantly support the management of the global trade in Cacatua species.