22 August 2022 in IEEE Transactions on Instrumentation and Measurement
Road potholes can cause discomforts to passengers and even traffic accidents to vehicles. Accurate segmentation of road potholes is an important capability for autonomous vehicles to ensure safe driving. Some methods on road-pothole segmentation use single-modal data (i.e., RGB images). The main challenge faced by these methods is that the visual appearance of road potholes is often close to road areas, making these networks difficult to distinguish them. Recent methods resort to fusing RGB images with depth/disparity images for pothole segmentation. However, their performance is still not satisfactory in real-world applications. To achieve superior results, this article proposes a novel data fusion network for road-pothole segmentation, where a channel attention fusion module and a dual attention fusion (DAF) module are designed to hierarchically fuse the RGB and disparity data. We evaluate our proposed network using a public dataset, and the experimental results demonstrate the superiority over the state-of-the-art networks.
6 November 2020 in IEEE Transactions on Cybernetics
In this article, we present a multiagent framework for real-time large-scale 3-D reconstruction applications. In SLAM, researchers usually build and update a 3-D map after applying nonlinear pose graph optimization techniques. Moreover, many multiagent systems are prevalently using odometry information from additional sensors. These methods generally involve extensive computer vision algorithms and are tightly coupled with various sensors. We develop a generic method for the key challenging scenarios in multiagent 3-D mapping based on different camera systems. The proposed framework performs actively in terms of localizing each agent after the first loop closure between them. It is shown that the proposed system only uses monocular cameras to yield real-time multiagent large-scale localization and 3-D global mapping. Based on the initial matching, our system can calculate the optimal scale difference between multiple 3-D maps and then estimate an accurate relative pose transformation for large-scale global mapping.
13 January 2022 in IEEE Robotics and Automation Letters
Deep learning-based image retrieval techniques for the loop closure detection demonstrate satisfactory performance. However, it is still challenging to achieve high-level performance based on previously trained models in different geographical regions. This letter addresses the problem of their deployment with simultaneous localization and mapping (SLAM) systems in the new environment. The general baseline approach uses additional information, such as GPS, sequential keyframes tracking, and re-training the whole environment to enhance the recall rate. We propose a novel approach for improving image retrieval based on previously trained models. We present an intelligent method, MAQBOOL , to amplify the power of pre-trained models for better image recall and its application to real-time multiagent SLAM systems. We achieve comparable image retrieval results at a low descriptor dimension (512-D), compared to the high descriptor dimension (4096-D) of state-of-the-art methods. We use spatial information to improve the recall rate in image retrieval on pre-trained models. Material related to this work is available at https://usmanmaqbool.github.io/why-so-deep .
21 July 2026 in Research Square
Quantifying blueberry fruit yield and maturity is important for evaluating yield potential in breeding trials, but manual measurement remains slow, labor-intensive, and costly. Object detection and classification networks offer a high-throughput solution, yet few studies validate image-based counts against hand-harvested ground truth while explicitly accounting for canopy occlusion. Hence, this study developed a multi-class berry detection pipeline for immature and mature berries and validated image-based estimates against hand-harvest counts across 32 diverse southern highbush blueberry genotypes. Among the models evaluated, YOLOv8x achieved the highest detection performance, with an mAP50 of 0.82 and an mAP50–95 of 0.66. External validation produced F1 scores ranging from 0.74 to 0.91 for berry maturity classes. However, image-based detections systematically underestimated hand-harvested fruit counts, with R² values ranging from 0.40 to 0.61. Fruit occlusion varied widely among genotypes, from 42% to 90%, indicating that canopy structure strongly affects berry visibility. Incorporating image-derived canopy architecture, color, and texture features improved predictions of berry counts and maturity. Partial Least Squares regression provided the best performance, increasing R² values of hand-harvested fruit counts, ranging from 0.52 to 0.74. These results show that accounting for canopy occlusion improves image-based estimation of blueberry yield and supports more accurate high-throughput phenotyping.