9 February 2022 in Fisheries Research
15 April 2024 in IEEE Sensors Journal
Pedestrian detection in thermal and visible images is crucial for various applications, such as surveillance, driver assistance, and autonomous driving. In this paper, we propose a novel fusion scheme that effectively integrates multimodal features to improve detection performance. Our approach relies on Cross-Modality Reference Module (CMRM) for exchanging complementary features extracted from different modalities, solving incorrect sensor dominance problem in rare untrained-for contexts. We also utilize modality-specific region proposal networks to explore potential candidates separately in each modality, ensuring accurate and reliable proposals. The fusion of region proposals is performed using the Multimodal Fusion Module (MFM) that employs an attention mechanism to combine features based on their attention scores. To improve the robustness of the model in practical scenarios, we introduce a group of new data augmentation techniques, which simulate real-world challenges. Experimental evaluations conducted on the public KAIST, CVC-14, and FLIR datasets demonstrate the effectiveness of our proposed method. The results show that our fusion scheme significantly outperforms the existing methods in terms of detection performance by as much as 16.4% in practical scenarios.
22 September 2023 in IEEE Transactions on Intelligent Vehicles
In recent years, radar has become a crucial part of road scene perception. In particular, radar increases sensing reliability in poor weather and lighting conditions. State-of-the-art deep learning methods require training, but the labeling of radar data needed to generate the required “ground truth” is time-consuming and requires expert knowledge, due to the confusing nature of radar signals. This limits the development of accurate radar models. To address the difficulty of annotating radar datasets, we propose a novel semi-supervised learning framework we call Automotive Radar Consistency (ARC), which enables the inclusion of unlabeled radar frames during training. This improves performance without adding manual labor. Our model learns object features based on micro-Doppler signatures from a time series of radar frames. We posit that the same object in both the forward and reverse temporal directions will share similar features, and we use this as a consistency regularization to encourage the model to learn how to distinguish targets. In addition, we propose Focal JS-divergence to alleviate over-fitting and address the class imbalance problem in semi-supervised learning, by focusing on the hard classes and samples in the unlabeled data. Our proposed method is a general training strategy that can be incorporated in most existing deep learning frameworks. Our experimental results on two public datasets with limited annotations show that our method significantly improves the performance of existing supervised methods. Under the same network architecture, our method outperforms the fully supervised method in object detection by as much as 36%.
1 January 1995 in Journal of Optical Communications
Article Analysis of Asymmetric Coplanar Strip Electrodes with a Buffer Layer in Integrated Electrooptics Devices was published on April 1, 1995 in the journal Journal of Optical Communications (volume 16, issue 2).