Search

[Objective] The extraction and change monitoring of cultivated land information is one of the hotspots of remote sensing application research. Northern Guangdong is the main grain base of Guangdong Province, and is the key area of cultivated land change monitoring by business management departments.[Method] In the present paper, using GF-2 and Sentinel-2 remote sensing images, combined with the phenological period of late rice in the study area, the vegetation index, humidity index, brightness index, color index and texture features were extracted for multi-scale segmentation, and the multi-scale image of paddy field extraction was constructed. The index difference image and time series multi feature difference image were classified to extract the paddy field area and evaluate the results.[Result]（i) The highest extraction accuracy of paddy field in time series multi feature difference image was 0.98,and the minimum difference between paddy field area and late rice sowing area was 240.05 hm2,and the best paddy field extraction effect was based on time series multi feature difference image;（ii）The difference of index feature needed to use the key phenological characteristics of crops and combine with multi-scale segmentation of image to improve the accuracy of paddy field extraction;（iii）The machine forest method has faster operation speed and higher classification accuracy in data classification with high dimensional features. [Conclusion] The research of the paper is to explore the method of high-resolution remote sensing in rapid and accurate updating of cultivated land information, which can provide support for the application of cultivated land management business. [ABSTRACT FROM AUTHOR]

Populational number of fish is of great significance in the intelligent aquaculture. An accurate and rapid target detection has been always obtained from the underwater images. Much attention is still paid on the single target during underwater fish detection so far. However, the overlapping target is largely limited to the applicative scenes. In this work, an overlapping fish detection model was proposed using image enhancement and an improved Faster-RCNN network, named after CP-Faster-RCNN. First, 15 healthy grass carps were fed in a test tank for 15 days, where the images of fish movement were collected by the equipped underwater camera. The total 2 077 available images were filtered to serve as the dataset for the modelling. The training, test, and validation set were divided, according to the rate of 6:2:2, respectively. In the training set, all recognized fishes in each image were labelled by the rectangle bounding boxes via a labelImg tool. Next, three most commonly-used detection models (YOLOv3-spp, SSD300, and YOLOv5x6), as well as the new proposed model (CP-Faster-RCNN) were trained using the training and test set, and then were verified by the validation set. Among them, the CP-Faster-RCNN model was optimized for such the overlapping fishes in the images. Hence, some improvements were made using the original Faster-RCNN model. The details were as follows. 1) The MSRCR combined with the adaptive median filtering was adapted to improve the definition of underwater images; 2) The ResNeXt101 network was served as the backbone network to enhance the feature extraction capability of the model; 3) A specific bilinear path aggregation network (Bi-PANet) with the Convolution Block Attention Module (CBAM) attention mechanism was designed to fully use the multi-scale feature maps, which was effectively reduced the interference of background information. 4) The PAM clustering was chosen to optimize the scale and number of initial anchors of the network, which was used to speed up the convergence of the model; 5) The Non-Maximum Suppression was replaced by the Soft Non-Maximum Suppression, in order to reduce the missed detection for the overlapping objects. The results showed that the mean Average Precision (mAP) values of CP-Faster-RCNN were 32.9, 12.3, and 6.7 percentage higher than those of YOLOv3-spp, SSD300, and YOLOv5x6, respectively, indicating the best performance of detection. Besides, 300 extra images were randomly selected from the validation set to test the actual performance of the four models. Statistical analysis demonstrated that there was the different detection accuracy at the different number of overlapping fishes in clusters. Once the number was from 2 to 5, the mAPs of CP-Faster-RCNN decreased orderly, which were 80.4%, 75.6%, 65.1%, and 55.6%, respectively. More importantly, the mAPs of CP-Faster-RCNN was rather higher than that of other three models in the same way, indicating the better suitable performance in the scenes of overlapping fishes. Last, five ablation tests were carried out to investigate the specific effects of five improvements, where the mAP was the index of assessment. It was found that the mAP of the CP-Faster-RCNN was 76.8%, which was the totally 8.4 percentage increase than that of the original Faster-RCNN network. The backbone network was replaced for the 5.7 percentage mAP increase, due to the more substantially complex model. Meantime, the pre-processing of dataset was also offered a 0.9 percentage increase of mAP. The other three improvements for the Faster-RCNN posed the positive impacts on the model complexity. All improvements were promoted the more accurate detection for the model. Therefore, the improved model can be expected to achieve the much more accurate fish detection, especially for the overlapping fish images in the complex underwater backgrounds. [ABSTRACT FROM AUTHOR]