Object detection is one of the most widespread applications for numerous Unmanned Aerial Vehicle (UAV) tasks. Due to the shooting angle and flying height of the UAV, compared with general scenarios, small objects account for a large proportion of aerial images, and common object detectors are not extremely effective in aerial images. Moreover, since the computing resources of UAV platforms are generally limited, the deployment of common detectors with a large number of parameters on UAV platforms is difficult. This paper proposes a lightweight object detector YOLO-UAVlite for aerial images. Firstly, the spatial attention module and coordinate attention module are modified and combined to form a novel Spatial-Coordinate Self-Attention (SCSA) module, which integrates spatial, location, and channel information to enhance object representation. On this basis, we construct a lightweight backbone, named SCSAshufflenet, which combines the Enhanced ShuffleNet (ES) network with the proposed SCSA module to improve feature extraction and reduce model size. Secondly, we propose an improved feature pyramid model, namely Slim-BiFPN, where we construct new lightweight convolutional blocks to reduce the information loss during the feature map fusion process while reducing the model weights. Finally, the localization loss function is modified to increase the bounding box regression rate while improving the localization accuracy. Extensive experiments conducted on the VisDrone-DET2021 dataset indicate that, compared with the YOLOv5-N baseline, the proposed YOLO-UAVlite reduces the number of parameters by 25.8% and achieves gains of 10.9% in mAP0.50. Compared with other lightweight detectors, both the mAP and the number of parameters are improved.

Precision agriculture becomes considerable important in agricultural modernization, and thus the demand of accurately extracting crop information from remotely sensed images based unmanned aerial vehicle (UAV) has increased sharply. The most contributing factors of crop classification precision are model selection and samples reliability. Crop recognition models have been obvious optimized under the booming deep learning, while our focus is on the latter factor. The article emphatically explored the best experimental configuration with two verification patterns based on three state-of-the-art image classification models to discuss the impact of sample quality on crop classification accuracy. The patterns referred to different composition ratio of training/verification samples and different spatial resolutions of UAV images. The former experiments revealed that crop types could be better recognized when the number of training sets is greater than or equal to the validation set. By comparing the accuracy different brought by resolutions, the other one illustrated that 40 meters is determined to be the best flight altitude, may balance the recognition accuracy and operating cost.

No abstract

No abstract