Task assignment is a key issue in mobile crowdsensing (MCS). Most existing work in this area has focused on the task assignment for the single platform scenario, which can cause considerable waste of limited human resources or reduced task completion rate due to potential spatial mismatching between distributions of users and tasks. In this article, we study multiplatform cooperative task assignment. The design goal is to maximize the social welfare while ensuring cooperative and individual rationality. We formulate this problem, transform it to a maximum value flow problem, and prove its NP-hardness. We first propose a greedy-maximum-flow-based task matching (GMTA) mechanism for interplatform task matching. In GMTA, there are two phases in each time slot: 1) in the former phase, earliest-deadline-first-based intraplatform optimal task assignment is carried out at each individual platform and 2) in the second phase, greedy-maximum-flow-based task matching is carried out to perform interplatform cooperative task assignment for those overloaded tasks in the first phase. We then enhance GMTA by designing an iterative-maximum-flow-based task matching (IMTA) mechanism, which is to achieve enhanced social welfare at the cost of increased computational overhead. We deduce time complexities of both mechanisms, and prove that they satisfy cooperative and individual rationality. Extensive simulations are conducted and the simulation results demonstrate the effectiveness of our proposed mechanisms.

Developing reliable, generalized, and accurate defect detection technology for photovoltaic (PV) manufacturers is particularly critical with the demand for production line expansion. Existing technologies perform well when handling independently and identically distributed (IID) data. However, their performance significantly reduces when they encounter domain shift problems, including style and instance bias, prompted by production line expansion. In this paper, we propose a novel Dual Bias Adjustment Network (DBAN) to enhance the generalization and reliability of PV defect detection. Specifically, we construct a Global Style-Generalized Contrastive Learning (GSCL), which uses nonlinear transformation functions and contrastive learning strategies to enhance model adaptability for different style changes and global discriminative ability, effectively overcoming the style bias problem. We design a Test-Time Prototype Adjustment (TTPA) that employs graph methods and prototype learning to adjust feature representations accurately. TTPA enhances prediction reliability during testing via dynamic prototype repositories and memory mechanisms, effectively addressing instance deviations. We conduct comprehensive experiments proving that DBAN achieves optimal performance, surpassing other advanced algorithms. Moreover, GSCL and TTPA add little inference time to the model, making them suitable for practical industrial applications. Finally, we conduct extensive experiments on the public domain-shifted PV dataset ELES, where our model achieves state-of-the-art performance in Single-domain generalized object detection. Note to Practitioners—This work proposes a practical defect detection solution, DBAN, enabling PV manufacturers to maintain reliable quality control across multiple production lines. The model can be directly integrated into existing inspection systems by deploying DBAN software on a central processing server that receives EL images from production lines. Trained with historical defect data from one production line, the model can automatically inspect products from expanded lines and continuously update its detection capabilities using real-time test data without retraining. DBAN enables practitioners to monitor multiple lines through a unified interface while maintaining high-quality standards, thus reducing equipment and labor costs. The system continuously enhances detection accuracy under varying manufacturing conditions, making it especially valuable for manufacturers seeking efficient, scalable production while ensuring product quality.

The Text-to-Image Person Re-identification (TI-ReID) task objective is to precisely identify the person’s images with the textual description of the person. The mainstream research methods focus on cross-modal aligning local features, and overlook the learning of intra-modal and cross-modal relationships between different features. This renders the person features lacking in high-level semantic information. To resolve such issues, we propose the Progressive Relationship-Mining Graph Network (RMGNet), including the Intra-Modal Relationship-Mining (IMRM) and the Cross-Modal Relationship-Mining (CMRM) module. These modules are employed to model and mine semantic relationship information among different features. Specifically, the IMRM module models and mines the high-level semantic interrelationships inherent in the image and text features. The CMRM module introduces the nearest neighbor method to model cross-modal semantic relationships to enhance the cross-modal semantic correspondence capabilities of person features. On this basis, we design the Adaptive Corner Center (Acc) loss and the Coarse-to-Fine Learning (C2FL) strategy. These ensure the network receives consistent and effective metric learning supervision throughout the entirety of the training process. To validate the efficacy of the proposed method, extensive experiments are conducted on three prevalent datasets: CHUK-PEDES, ICFC-PEDES, and RSTPReid. The achieved mAP of 70.59%, 41.62%, and 49.58% surpassed those current state-of-the-art methods.

Mobile crowdsensing is a sensing paradigm using mobile users’ smart devices to perform sensing tasks, which has attracted much attention due to its low system cost, high flexibility, and wide coverage. In this paper, we study the hybrid sensing online task allocation problem for maximizing the total quality of completed tasks under given budget constraint. We formulate this problem as a 0-1 integer programming. To address this problem, we propose an efficient hybrid sensing based online task assignment algorithm (HSTA), which consists of two major components: Expected task completion quality based opportunistic user recruitment and participatory user recruiting and path planning. We present the detailed algorithm design of HSTA and deduce its computational complexity. Simulation results demonstrate the effectiveness of the proposed HSTA algorithm.

Task assignment is a critical issue in mobile crowd-sensing, which is aimed to maximize the number of completed tasks subject to budget constraints. However, existing work in this aspect did not consider the correlation between the tasks submitted by the same task requester. That is, tasks in the same subset from the same task requester are often correlated such that they are considered completed only when all of them are completed, and partial completion of them are useless. This requirement largely affects the performance of existing algorithms for the assignment of such partially correlated tasks. In this paper, we formulate the problem of maximizing the total number of completed tasks subject to such correlation and also budget constraints as an integer programming problem. We propose two greedy algorithms, one is requester happiness utility based algorithm and the other is minimum task remaining subset first algorithm. We present design details of both algorithms and deduce their computational complexities. Numerical results demonstrate that these two algorithms can significantly outperform the existing work.

With the rapid growth of Internet of Things and proliferation of handheld smart devices, mobile crowdsensing has been regarded as an effective sensing paradigm due to its high scalability, low cost, and wide coverage. In this paper, we study hybrid task assignment where semi-opportunistic and participatory users co-exist for task executions while tasks are delay sensitive and have heterogeneous qualities. The design objective is to maximize the total quality of completed tasks subject to a total budget shared by both types of users. We formulate this problem as an integer programming problem. We propose an efficient hybrid users based task assignment algorithm (referred to as HU-TSA), which works in an iterative way as follows. It first selects the top n (initially, n = 1) semi-opportunistic users in terms of quality-cost ratio for task assignment. It then clusters the remaining tasks into different regions based on their closeness and then performs utility based optimized user-region binding and standardized task density based path planning for the participatory users. It repeats the above process over all possible values of n to seek an optimal budget splitting between the two types of users for improved performance. We present the detailed design description of HU-TSA and deduce its computational complexity. Extensive simulations are carried out and the results show the effectiveness of HU-TSA by comparing with existing algorithms.

The surface of a multicrystal solar cell shows multiple crystal grains of random shapes and sizes. It creates an inhomogeneous texture in the surface, which brings great difficulty to automatic crack detection of polycrystalline solar surface. As a perceptual grouping approach, tensor voting can extract curvilinear structures such as lines and curves from noisy, binary data in 2-D or 3-D, without invoking specific object or model. However, traditional tensor voting can be susceptible to the gap problem and structural noise. To address the problems mentioned above, a new iterative tensor voting algorithm is presented, which efficacy bases on iterative refinements of the curvilinear structures. By combining the proximity and continuity of Gestalt principles, in each iteration step, a new decay function is redefined according to the difference of angle between the voter and receiver to rebuild the voting field, which makes the points that lie on curvilinear structures vote more information (a bigger tensor) to the ones with the same attribute. The proposed method can solve the gap problem and is robust to structural noises. The experimental results show that the proposed method can detect crack on the inhomogeneous textured surface and achieve an average detection rate of 95.2% on the industrial data set. Note to Practitioners-Automatic vision-based defect detection on the solar cell is difficult due to inhomogeneous texture and low contrast between defects and background in the surface. In order to solve these problems, by combining the proximity and continuity of Gestalt principles, this article proposed a new iterative tensor voting algorithm which can refine the curvilinear structures with iterations. Experiments have shown that the proposed method can detect crack under the interference of inhomogeneous texture and complex background.

The automatic defects detection for solar cell electroluminescence (EL) images is a challenging task, due to the similarity of defect features and complex background features. To address this problem, in this article a novel complementary attention network (CAN) is designed by connecting the novel channel-wise attention subnetwork with spatial attention subnetwork sequentially, which adaptively suppresses the background noise features and highlights the defect features simultaneously by employing the complementary advantage of the channel features and spatial position features. In CAN, the novel channel-wise attention subnetwork applies convolution operation to integrate the concatenated and discriminative output features extracted by global average pooling layer and global max pooling layer, which can make fully use of these informative features. Furthermore, a region proposal attention network (RPAN) is proposed by embedding CAN into region proposal network in faster R-CNN (convolution neutral network) to extract more refined defective region proposals, which is used to construct a novel end-to-end faster RPAN-CNN framework for detecting defects in raw EL image. Finally, some experimental results on a large-scale EL dataset including 3629 images, 2129 of which are defective, show that the proposed method performs much better than other methods in terms of defects classification and detection results in raw solar cell EL images.

Automatic defect detection on strip steel surfaces is a challenging task in computer vision, owing to miscellaneous patterns of defects, disturbance of pseudodefects, and random arrangement of gray-level in background. In this paper, a novel template establishment is presented. Further, a simple guidance template-based algorithm for strip steel surface defect detection is proposed. First, a large number of defect-free images are collected to obtain the statistical characteristic of normal textures. Second, for each given test image, the initial template is built according to the statistical characteristic and the size of test image. Then, a sorting operation is applied to the given test image. Further, by updating the initial template, a unique guidance template is generated based on specific intensity distribution of the sorted test image. So far, the background of each test image is approximately reconstructed in the guidance template. Finally, based on pixel-wise detection, the defects can be located accurately by subtraction operation between the guidance template and sorted test image, reverse sorting operation, and adaptive threshold determination. Experimental results show that the proposed method is both efficient and effective. It achieves a better average detection rate of 96.2% on a data set including 1500 test images.