Narrow Results

Segment Anything Model (SAM), an advanced universal image segmentation model trained on an expansive visual dataset, has set a new benchmark in image segmentation and computer vision. However, it faced challenges when it came to distinguishing between shadows and their backgrounds. To address this, we proposed ShadClips, which consists of SAM-optimizer and SONet. It has dramatically enhanced SAM’s ability to segment shadow images, differentiating between the background and both soft and hard shadows adeptly. Due to its dependence on pixel point inputs, the SAM-Optimizer interface could do better. This method presents challenges, especially when dealing with long, extended shadows. To make the user experience more intuitive and effective, we incorporated the capabilities of CLIPs. Therefore, simple text descriptions like “A photo of a shadow” can be used to guide the SAM-Optimizer, allowing it to select the most relevant shadow mask from SAM’s comprehensive category list. Meanwhile, we introduce SONet to shadow removal. A large number of experiments on ISTD/SRD prove that the proposed method is effective and satisfactory. The source code of the ShadClips can be accessed from https://github.com/zhangbaijin/SAM-helps-Shadow.

We present an automated and complete camera-based monitoring system that makes use of low-level color features to perform detection, tracking and recognition of multiple people in video sequence. Specifically, the system employs a novel coverage check-up method to segment detected foreground regions into isolated people and then localize each of them. During tracking, the appearances of people are modeled by their color histograms so that the system can keep aware of their identities and recognize them after occlusions by maximizing the joint likelihood. To make the recognition more robust against shadows or changes of background illumination, the system also incorporates a shadow removal scheme to suppress shadow effects and hence improve the quality of color histogram. The proposed system has been used to identify people who re-enter the field of view of a monitoring camera in a closed-environment. Experimental results of real video data demonstrate the efficacy of the proposed people monitoring system.

To solve the problem of road recognition when the robot is driving on the sidewalk, a novel sidewalk detection algorithm from the first-person perspective is proposed, which is crucial for robot navigation. The algorithm starts from the illumination invariance graph of the sidewalk image, and the sidewalk “seeds” are selected dynamically to get the sidewalk features for unsupervised feature learning. The final sidewalk region will be extracted by multi-threshold adaptive segmentation and connectivity processing. The key innovations of the proposed algorithm are the method of illumination invariance based on PCA and the unsupervised feature learning for sidewalk detection. With the PCA-based illumination invariance, it can calculate the lighting invariance angle dynamically to remove the impact of illumination and different brick colors’ influence on sidewalk detection. Then the sidewalk features are selected dynamically using the parallel geometric structure of the sidewalk, and the confidence region of the sidewalk is obtained through unsupervised feature learning. The proposed method can effectively suppress the effects of shadows and different colored bricks in the sidewalk area. The experimental result proves that the F-measure of the proposed algorithm can reach 93.11% and is at least 7.7% higher than the existing algorithm.