When working with objects on a smaller scale, higher detection accuracy and faster detection speed are desirable features. Researchers aim to endow drones with these attributes in order to improve performance when patrolling in controlled areas for object detection. In this paper, we propose an improved YOLOv7 model. By incorporating the variability attention module into the backbone network of the original model, the association between distant pixels is increased, resulting in more effective feature extraction and, thus, improved model detection accuracy. By improving the original network model with deformable convolution modules and depthwise separable convolution modules, the model enhances the semantic information extraction of small objects and reduces the number of model parameters to a certain extent. Pretraining and fine-tuning techniques are used for training, and the model is retrained on the VisDrone2019 dataset. Using the VisDrone2019 dataset, the improved model achieves an mAP₅₀ of 52.3% on the validation set. Through the visual comparative analysis of the detection results in our validation set, we find that the model shows a significant improvement in detecting small objects compared with previous iterations.

The objects in UAV aerial images have multiple scales, dense distribution, and occlusion, posing considerable challenges for object detection. In order to address this problem, this paper proposes a real-time multi-scale object detection method based on an improved YOLOv7 model (ATS-YOLOv7) for UAV aerial images. First, this paper introduces a feature pyramid network, AF-FPN, which is composed of an adaptive attention module (AAM) and a feature enhancement module (FEM). AF-FPN reduces the loss of deep feature information due to the reduction of feature channels in the convolution process through the AAM and FEM, strengthens the feature perception ability, and improves the detection speed and accuracy for multi-scale objects. Second, we add a prediction head based on a transformer encoder block on the basis of the three-head structure of YOLOv7, improving the ability of the model to capture global information and feature expression, thus achieving efficient detection of objects with tiny scales and dense occlusion. Moreover, as the location loss function of YOLOv7, CIoU (complete intersection over union), cannot facilitate the regression of the prediction box angle to the ground truth box—resulting in a slow convergence rate during model training—this paper proposes a loss function with angle regression, SIoU (soft intersection over union), in order to accelerate the convergence rate during model training. Finally, a series of comparative experiments are carried out on the DIOR dataset. The results indicate that ATS-YOLOv7 has the best detection accuracy (mAP of 87%) and meets the real-time requirements of image processing (detection speed of 94.2 FPS).

Path planning is crucial in the scheduling and motion planning of multiple robots. However, solving multi-robot path-planning problems efficiently and quickly is challenging due to their high complexity and long computational time, especially when dealing with many robots. This paper presents a unified mathematical model and algorithm for the path planning of multiple robots moving from one formation to another in an area with obstacles. The problem was initially simplified by constructing a cost matrix, and then the route planning was achieved by integrating an elite enhanced multi-population genetic algorithm and an ant colony algorithm. The performance of the proposed planning method was verified through numerical simulations in various scenarios. The findings indicate that this method exhibits high computational efficiency and yields a minimal overall path distance when addressing the path-planning problem of a multi-robot formation reconstruction. As a result, it holds promising potential for the path-planning problem of a multi-robot formation reconstruction.