In recent years, thermal imaging cameras are widely used in the field of intelligent surveillance because of their special imaging characteristics and better privacy protection properties. However, due to the low resolution and fixed location for current thermal imaging cameras, it is difficult to effectively identify human behavior using a single detection method based on skeletal keypoints. Therefore, a self-update learning method is proposed for fixed thermal imaging camera scenes, called the behavioral parameter field (BPF). This method can express the regularity of human behavior patterns concisely and directly. Firstly, the detection accuracy of small targets under low-resolution video is improved by optimizing the YOLOv4 network to obtain a human detection model under thermal imaging video. Secondly, the BPF model is designed to learn the human normal behavior features at each position. Finally, based on the learned BPF model, we propose to use metric modules, such as cosine similarity and intersection over union matching, to accomplish the classification of human abnormal behaviors. In the experimental stage, the living scene of the indoor elderly living alone is applied as our experimental case, and a variety of detection models are compared to the proposed method for verifying the effectiveness and practicability of the proposed behavioral parameter field in the self-collected thermal imaging dataset for the indoor elderly living alone.

Optical coherence tomography angiography (OCTA) is a new non-invasive imaging technology that provides detailed visual information on retinal biomarkers, such as the retinal vessel (RV) and the foveal avascular zone (FAZ). Ophthalmologists use these biomarkers to detect various retinal diseases, including diabetic retinopathy (DR) and hypertensive retinopathy (HR). However, only limited study is available on the parallel segmentation of RV and FAZ, due to multi-scale vessel complexity, inhomogeneous image quality, and non-perfusion, leading to erroneous segmentation. In this paper, we proposed a new adaptive segmented deep clustering (ASDC) approach that reduces features and boosts clustering performance by combining a deep encoder–decoder network with K-means clustering. This approach involves segmenting the image into RV and FAZ parts using separate encoder–decoder models and then employing K-means clustering on each part separated by the encoder–decoder models to obtain the final refined segmentation. To deal with the inefficiency of the encoder–decoder network during the down-sampling phase, we used separate encoding and decoding for each task instead of combining them into a single task. In summary, our method can segment RV and FAZ in parallel by reducing computational complexity, obtaining more accurate interpretable results, and providing an adaptive approach for a wide range of OCTA biomarkers. Our approach achieved 96% accuracy and can adapt to other biomarkers, unlike current segmentation methods that rely on complex networks for a single biomarker.

Class-agnostic binary segmentation identifies objects that are similar or very different from the complex background, including salient object detection (SOD) and camouflage object detection (COD). Most existing models only focus on a specific type of foreground and background segmentation by employing the global modeling ability of transformers, without explicitly explaining or eliminating the discrepancy between these two different distributions. They also suffer from inefficient local feature learning and inadequate feature aggregation. To make binary segmentation research more accessible and trivially generalized, we introduce a novel unified uncertainty-aware paradigm, called uncertainty-aware feature reassembly (UAFer). Specifically, the Spatial Feature Reassembly (SFR) module is presented to formulate the uncertainty of binary segmentation map as the variance of generalized Bernoulli distribution and entropy from two perspectives. Our transformer-based model is then trained to prioritize regions of higher certainty, obtaining more confident and accurate predictions during the feature upsampling. Moreover, the Channel Feature Reassembly (CFR) with adjacent feature aggregation is designed to facilitate an iterative exploration of channel integrity. This iterative learning process enhances the interaction of neighboring channel features; thus, improving universal object information decoding efficiency. Extensive quantitative and qualitative evaluations demonstrate that our proposed UAFer consistently outperforms the state-of-the-art models across three challenging domains including SOD, COD, and polyp segmentation (POLYP). The implementation codes for our approach will be publicly available at https://github.com/zihaodong/UAFR.