Low-frame-rate (LFR) Multi-Object Tracking (MOT) is crucial for efficient tracking on edge devices, as it significantly reduces computational and storage demands. However, existing trackers struggle in LFR settings due to large temporal gaps, extreme appearance changes, and motion non-linearity. While Graph Neural Network (GNN)-based trackers are effective at associating objects across these gaps, most operate offline, which prevents their use for online tracking. To address these limitations, we propose GLoMOT, a novel online GNN-based Low-Frame-Rate Multi-Object Tracker designed for robust performance in LFR videos. To bridge the large temporal gaps, we introduce a Dynamic Node Buffer Pool. This acts as a long-term memory, caching the states of absent objects to enable their robust re-association. To tackle extreme motion uncertainty, we propose an adaptive context-aware module that dynamically adjusts the weights of positional and appearance features, generating more robust features for predicting node connections. Furthermore, we propose a pseudo-depth feature calculation method. This provides the GNN with critical geometric context, which helps resolve spatial ambiguity arising from occlusions. Extensive experiments on several public MOT benchmarks, including DanceTrack, MOT17, and VisDrone, demonstrate GLoMOT's effectiveness and superiority, particularly in challenging Low-Frame-Rate conditions.

In this paper, we introduce a new dataset for air conditioner refrigerant leak smoke detection, called ACRL-10K. The dataset is designed to develop algorithms for detecting refrigerant leak smoke faults during air conditioner recycling. It contains a total of 10,724 images covering three common scenarios of air conditioner refrigerant leak: loading port, refrigerant extraction, and disassembly. All images are sourced from 656 video segments of real air conditioner recycling scenarios, captured by surveillance cameras deployed on an environmental company’s recycling production line. The annotations for the refrigerant leak smoke in the images are performed by industry experts to ensure high accuracy and consistency. To the best of our knowledge, ACRL-10K is the first dataset specifically designed for refrigerant leak smoke detection. Based on the ACRL-10K dataset, we present the performance of mainstream object detectors, including the YOLO series, as a baseline to conduct the following work: 1) preliminarily summarize the challenges of using the dataset for refrigerant leak smoke detection; 2) show the detection results of benchmark methods; and 3) make a comparison to identify the strengths and weaknesses of the baseline algorithms. In practice, the ACRL-10K dataset would hopefully advance research and applications in refrigerant leak early warning during air conditioner dismantling and recycling processes.

In the process of air conditioner dismantling and recycling at environmental protection companies, there is a risk of refrigerant leak smoke emissions. The release of fluorinated gases poses threats to both the environment and human health, making the detection of refrigerant leak smoke during dismantling crucial for environmental protection. However, existing smoke detection algorithms struggle to achieve high detection accuracy due to the low density and subtle characteristics of refrigerant leak smoke. In this paper, we observe the characteristics of leak smoke, which frequently appears near workers but rarely overlaps with them, thus adding a worker_fog co-location label to the previously established refrigerant leak detection dataset, ACRL-10K. This label assists the model in precisely localizing refrigerant leak smoke. To leverage the spatial correlation between workers and leak smoke, we propose a double-head yolo model, DHYOLO. The first detection head performs initial predictions on worker_fog regions, and the second head refines these predictions within the initially identified areas, enabling focused detection of refrigerant leak smoke. Additionally, we propose a multi-branch aggregation module, VoVRepGSCSP, which uses a multi-branch structure with convolutional kernels of various sizes to effectively capture image details, therefore enhancing YOLOv11’s sensitivity to refrigerant leak smoke. Experimental results on the supplemented ACRL-10K dataset demonstrate that DH-YOLO achieves an AP50 of up to 81.5% in leak detection tasks. Compared with the original YOLOv11, DH-YOLO improves AP50 across all sized models by 1.2% to 3.0%. In industrial applications, DH-YOLO shows promise for refrigerant leak warning in air conditioner dismantling processes.

Because the power grid system is easily damaged by external forces from construction vehicles, performing early warning of construction vehicles through object detection is of practical significance for protecting the safety of the power grid. However, accurate detection of engineering vehicles under complex and diverse scenarios is a challenging task. When the existing advanced anchor-free probabilistic two-stage detector CenterNet2 is directly applied to this task, the effect is unsatisfactory. The essential reason is that construction vehicles such as excavators, tower cranes, and truck cranes are different from ordinary objects. They usually have stretchable long robotic arms, resulting in serious deviation of the center point of the bounding box and excessive coverage of the background area by the detection bounding box. Therefore, this paper has made beneficial improvements to two-stage CenterNet2 model. Firstly, it proposes an adaptive positive sample selection algorithm based on Gaussian kernel function to improve the insufficient and unreasonable positive and negative sample sampling in the first-stage regional candidate network. Secondly, it furthers proposes a joint prediction of location accuracy and classification confidence with the IoU-aware category labels, which improves the bounding box ranking during the second-stage network and prevents some potential prediction results being mistakenly filtered out in the post-processing stage. The experimental results on our self-built engineering vehicle dataset indicate that the proposed method effectively alleviates the above problems and achieves promising results in actual engineering vehicle detection.

Recently, researchers have introduced diffusion models into multiple object tracking (MOT) tasks. However, existing diffusion-based MOT methods, such as DiffusionTrack, have significant limitations, including frequent ID switching, reduced performance when tracking nonlinear motion objects, and long inference time. To this end, we propose a more effective diffusion-based multiple object tracker named DiffusionMOT. In particular, we propose a mixed intersection over union (IoU) and Re-Identification (ReID) method for trajectory matching, which effectively reduces incorrect matches. Meanwhile, we propose a secondary calibration method for trajectory boxes, improving the accuracy of the generated detection boxes. Moreover, we introduce the parallel sampling technique from the field of image generation into object tracking and propose a parallel sampling module to enhance the model's inference speed while maintaining tracking accuracy. Furthermore, we design a pair-based two-stage matching (PTM) pipeline to more effectively utilize potential detection information. Extensive experiments on several public MOT benchmarks, including DanceTrack, SportsMOT, MOT20, and MOT17, demonstrate that our approach achieves state-of-the-art (SOTA) performance. The code and models are available at https://github.com/sad123-yx/DiffusionMOT.