Research and Application of a Multitarget Detection Algorithm Based on Improved YOLOv8 for Indoor Objects

This study focuses on enhancing the intelligence level of assisted living robots to meet the needs of older adults with disabilities. The goal is to achieve efficient multitarget detection of everyday objects and to improve the accuracy and recall of the detection algorithm. To this end, an improved YOLOv8 algorithm (YOLOv8-CBW3) is proposed. First, the GAM global attention mechanism is embedded in the backbone network of YOLOv8 to improve the sensitivity of the backbone network to the important feature information and reduce the attention to the irrelevant features, and it is determined that the GAM global attention mechanism will be embedded in the backbone network of YOLOv8 after comparing and analyzing the GAM with the attention mechanisms of CBAM, SE, and ECA; second, at the neck layer, the original PAN-FPN network structure is replaced with the BiFPN structure at the neck layer to realize bidirectional cross-scale connectivity and weighted feature fusion. In addition, a small-target detection layer is added to the original YOLOv8 model to enhance the detection capability for small-scale targets. Finally, the WIoUv3 loss is used instead of the CIoU loss as the localization regression loss function, which reduces the influence of low-quality anchor frames and enhances the Model’s focus on global information, thus improving the accuracy of target object detection. After 300 rounds of testing on 3000 data samples, the YOLOv8 - CBW3 algorithm achieves a detection accuracy of 95.11%, a recall of 94.60%, and an average precision of 95.23%, which are improvements of 2.78% and 3.72% in accuracy and recall, respectively, compared with YOLOv8n. A comparison with other popular models shows that YOLOv8 - CBW3 has strong generalizability, localization performance, detection ability and robustness. To verify that YOLOv8-CBW3 has strong generalizability, a comparative analysis is conducted on the VOC2007 public dataset, which shows through the data that its detection ability is still optimal, and it provides a reference solution for subsequent similar problems.