Digital agriculture and smart farming require crop health monitoring methods that balance detection accuracy with computational cost. Rice leaf diseases threaten yield, while field images often contain small multi-scale lesions, variable illumination and cluttered backgrounds. This paper investigates SCD-YOLOv11n, a lightweight detector designed with these constraints in mind. The model replaces the YOLOv11n backbone with a StarNet backbone and integrates a C3k2-Star module to enhance fine-grained, multi-scale feature extraction. A Detail-Strengthened Cross-scale Detection (DSCD) head is further introduced to improve localization of small lesions. On this architecture, we design a DepGraph-based mixed group-normalization pruning rule and apply channel-wise feature distillation to recover performance after pruning. Experiments on a public rice leaf disease dataset show that the compressed model requires 1.9 MB of storage, achieves 97.4% mAP@50 and 76.2% mAP@50:95, and attains a measured speed of 184 FPS under the tested settings. These results provide a quantitative reference for designing lightweight object detectors for rice disease monitoring in digital agriculture scenarios.

Object Detection in Complex Indoor Scenes is designed to identify and categorize objects in indoor settings, with applications in areas such as smart homes, security surveillance, and home service robots. It forms the basis for advanced visual tasks including visual question answering, video description generation, and instance segmentation. Nonetheless, the task faces substantial hurdles due to background clutter, overlapping objects, and significant size differences. To tackle these challenges, this study introduces an indoor object detection approach utilizing an enhanced DINO framework. To cater to the needs of indoor object detection, an Indoor-COCO dataset was developed from the COCO object detection dataset. The model incorporates an advanced Res2net as the backbone feature extraction network, complemented by a deformable attention mechanism to better capture detailed object features. An upgraded Bi-FPN module is employed to replace the conventional feature fusion module, and SIoU loss is utilized to expedite convergence. The experimental outcomes indicate that the refined model attains an mAP of 62.3%, marking a 5.2% improvement over the baseline model. These findings illustrate that the DINO-based indoor object detection model exhibits robust generalization abilities and practical utility for multi-scale object detection in complex environments.

With the advancement of science and technology, pollution in rivers and water surfaces has increased, impacting both ecology and public health. Timely identification of surface waste is crucial for effective cleanup. Traditional edge detection devices struggle with limited memory and resources, making the YOLOv8 algorithm inefficient. This paper introduces a lightweight network model for detecting water surface litter. We enhance the CSP Bottleneck with a two-convolutions (C2f) module to improve image recognition tasks. By implementing the powerful intersection over union 2 (PIoU2), we enhance model accuracy over the original CIoU. Our novel Shared Convolutional Detection Head (SCDH) minimizes parameters, while the scale layer optimizes feature scaling. Using a slimming pruning method, we further reduce the model’s size and computational needs. Our model achieves a mean average precision (mAP) of 79.9% on the surface litter dataset, with a compact size of 2.3 MB and a processing rate of 128 frames per second, meeting real-time detection requirements. This work significantly contributes to efficient environmental monitoring and offers a scalable solution for deploying advanced detection models on resource-constrained devices.

In the realm of construction site monitoring, ensuring the proper use of safety helmets is crucial. Addressing the issues of high parameter values and sluggish detection speed in current safety helmet detection algorithms, a feature-enhanced lightweight algorithm, LG-YOLOv8, was introduced. Firstly, we introduce C2f-GhostDynamicConv as a powerful tool. This module enhances feature extraction to represent safety helmet wearing features, aiming to improve the efficiency of computing resource utilization. Secondly, the Bi-directional Feature Pyramid (BiFPN) was employed to further enrich the feature information, integrating feature maps from various levels to achieve more comprehensive semantic information. Finally, to enhance the training speed of the model and achieve a more lightweight outcome, we introduce a novel lightweight asymmetric detection head (LADH-Head) to optimize the original YOLOv8-n’s detection head. Evaluations on the SWHD dataset confirm the effectiveness of the LG-YOLOv8 algorithm. Compared to the original YOLOv8-n algorithm, our approach achieves a mean Average Precision (mAP) of 94.1%, a 59.8% reduction in parameters, a 54.3% decrease in FLOPs, a 44.2% increase in FPS, and a 2.7 MB compression of the model size. Therefore, LG-YOLOv8 has high accuracy and fast detection speed for safety helmet detection, which realizes real-time accurate detection of safety helmets and an ideal lightweight effect.

With the rapid development of science and technology, online shopping has gradually changed the way people buy goods because of its good quality and fast circulation. Therefore, online shopping has become one of the important modern shopping modes. With the development of the Internet, there are more and more channels to find product images and accompanying descriptive texts. How to retrieve the required goods accurately and efficiently is one of the important problems to be solved urgently. The existing traditional image retrieval methods mostly focus on the semantic information of the modality itself, and learn the binary code through quantization to find the similarity between the modalities. The heterogeneity of different types of modalities needs further discussion. Therefore, it is difficult to explain the low average accuracy of commodity image retrieval. Different from the traditional linear regression model retrieval method, this study uses a polynomial regression model method, which focuses on directly using polynomial regression to guide hash learning. The results show that the average accuracy of multimodal commodity retrieval using different methods to extract commodity image features is obviously better than that of traditional linear regression model, and polynomial regression model is the main factor to guide hash learning. When the code length is 128 bits, the average accuracy of LBP and TF_IDF is the highest. By analyzing the reasons why the average retrieval accuracy can be improved between different modes with the same semantics, the target commodity image can be searched to the greatest extent, saving more space cost and time cost.

This article studies consumer online review behaviors based on recommendation reward programs. It mainly studies the influence of different types of rewards in the recommendation reward plan on consumers’ online review behavior. Through the questionnaire survey, the results show that consumers are more inclined to choose monetary rewards as their return in the recommendation reward program. At the same time, different rewards in the recommendation reward plan, consumer product satisfaction, and the interaction of the two also have a certain impact on consumers’ online review behavior. This article divides the amount of rewards into high rewards and low rewards. When the consumer’s satisfaction reaches a certain level, low rewards in the referral reward program will bring more benefits to the merchants than high rewards. High rewards will only have a greater effect on consumers who are less satisfied with the product. When consumer product satisfaction is not high, and the reward limit set by the recommendation reward plan is low, consumers’ perception of fairness will cause them not to conduct online evaluation behaviors, even if the reward limit is high, the effect is not significant.

Wavelet Transform Coding Scheme is very promising due to its high coding efficiency. The coder of this scheme provides the coded bit stream can be truncated at any point adapting to best effort delivery of network. In this work, we investigate R-D (Rate-Distortion) model for each subband based on statistical property of coefficients. Then, a constrained bitrate allocation method is derived by exploiting the R-D performance of the coder. Experimental results show that the proposed method can provides bitrate-distortion tradeoff, and achieves target bitrate allocation and guarantees both good subjective and objective quality.

This paper presented a new method for 2D plus depth stereoscopic video coding. This method gave the scalable stereoscopic video coding framework based on wavelet. Proposed depth temporal compensated filtering (DCTF) realized the depth temporal scalable. The framework of encoder, extractor and decoder were given. The experimental results showed that the 2D and depth sequences temporal, space and quality scalable were realized.

This paper presents a new method for 2D to 3D video conversion based on motion information. This method exploits the different relations of pixels matching after motion estimation to generate depth map of the 2D video. On the edge of moving object, pixels matching degree is utilized to judge that the pixel belongs to foreground or background. The contour of moving object will become more distinct. Furthermore, to the pixel which hasn't get correct matching, corresponding approach is given according to the object motion. The experimental results show that the sawtooth effect of depth map significantly reduced by proposed method. The quality of 3D video is improved.