In the current age of data explosion, the amount of data has reached incredible proportions. Digital image data constitute most of these data. With the development of science and technology, the demand for networked work and life continues to grow. Cloud computing technology plays an increasingly important role in life and work. This paper studies the optimization methods for cloud computing image data recognition models. The parallelization and task scheduling of the remote-sensing image classification model SCSRC based on spatial correlation regularization and sparse representation are studied in a cloud computing platform. First, cloud detection technology, combined with the dynamic features of the edge overlap region, is implemented in cloud computing mode. For image edge overlap region detection, the SCSRC method is implemented on a single machine, and the time performance of the method is analysed experimentally, which provides a basis for parallelization research under the cloud computing platform. Finally, the speedup and expansion ratio of the SK-SCSRC algorithm are determined by experiment, and MR-SCSRC and SK-SCSRC are compared. The simulation results show that, compared to previous methods, the method of image edge overlap detection is more accurate and the image fusion is better, which improves the image recognition ability in the overlap region and demonstrates the performance improvement of the MR-SCSRC algorithm under scheduling. This method addresses the shortcomings of Hadoop’s existing scheduler and can be integrated into remote-sensing cloud computing systems in the future.

With the continuous advancement of education informatization, classroom behavior analysis has become an important tool to improve teaching quality and student learning outcomes. However, student classroom behavior recognition methods still face challenges such as occlusion, small objects, and environmental interference, resulting in low recognition accuracy and lightweight performance. To address the above problems, this study proposes a lightweight student behavior recognition model based on Inverted Residual Mobile Block (IMRMB-Net). Specifically, this study designs a lightweight feature extraction module, IMRMB, from the images of the backbone network to be able to better capture contextual information and improve the recognition of occluded objects while saving computational resources. Using DySample, the neck network reconsiders the initial sampling position and the moving range of the offset from the point sampling perspective to accurately recognize small object behaviors in course scenes. Meanwhile, a new loss function, Focaler-ShapeIoU, is designed in this study, aiming to improve the learning ability and robustness of the model to different samples thus further solving the occlusion problem. Experiments in UK_Dataset show that IMRMB-Net has high accuracy (mAP@50 = 93.3%, mAP@50:95 = 78.7%) and lightweight performance (FPS = 60.37, Params = 7.32MB, GFLOPs = 23.8G). Meanwhile, this study verifies that IMRMB-Net can effectively solve the occlusion problem in classroom scenarios through experiments on the UK_Dataset and SCB_Dataset occlusion subsets. In addition, this study verifies the generalization ability and the ability to recognize small targets of IMRMB-Net on the VisDrone2021 dataset.