This study proposed an interpretable multi-scale infrared small object detection network (IMD-Net) design method to improve the precision of infrared small object detection and contour segmentation in complex backgrounds. To this end, a multi-scale object enhancement module was constructed, which converted artificially designed features into network structures. The network structure was used to enhance actual objects and extract shallow detail and deep semantic features of images. Next, a global object response, channel attention, and multilayer feature fusion modules were introduced, combining context and channel information and aggregated information, selected data, and decoded objects. Finally, the multiple loss constraint module was constructed, which effectively constrained the network output using multiple losses and solved the problems of high false alarms and high missed detections. Experimental results showed that the proposed network model outperformed local energy factor (LEF), self-regularized weighted sparse model (SRWS), asymmetric contextual modulation (ACM), and other state of the art methods in the intersection-over-union (IoU) and F_measure values by 10.8% and 11.3%, respectively. The proposed method performed best on the currently available datasets, achieving accurate detection and effective segmentation of dim and small objects in various infrared complex background images.

Crop area statistics and yield prediction will affect adjustment of agricultural policy, to a certain extent. With the development of computer automatic classification techniques, the performance of classifiers are influenced by feature preprocessing and sample selection. Remote sensing classification according to spectral information is affected by false negatives and miscalculation in the complex spectrum area. Corn planting areas and other land-cover objects contain different surface structures and smoothness; other vegetation and villages have coarse textures. This paper introduces texture information based on a Gabor filter group to enrich land-cover information and establish a spectrum-texture feature set. With more samples, the algorithm efficiency is greatly affected. This paper proposes an improved fuzzy ARTMAP (FAM) with an adaptive boost strategy, namely Adaboost_FAM. Weak classifiers are trained to construct strong classifiers so as to improve operation efficiency. Meanwhile, classification accuracy will not be greatly improved. Experimental results indicate that the proposed method improves extraction accuracy when compared to classical algorithms, and improves efficiency when compared to algorithms which contain a great number of samples.