Abstract:We propose an end-to-end ensemble method for person re-identification (ReID) to address the problem of overfitting in discriminative models. These models are known to converge easily, but they are biased to the training data in general and may produce a high model variance, which is known as overfitting. The ReID task is more prone to this problem due to the large discrepancy between training and test distributions. To address this problem, our proposed ensemble learning framework produces several diverse and accurate base learners in a single DenseNet. Since most of the costly dense blocks are shared, our method is computationally efficient, which makes it favorable compared to the conventional ensemble models. Experiments on several benchmark datasets demonstrate that our method achieves state-of-the-art results. Noticeable performance improvements, especially on relatively small datasets, indicate that the proposed method deals with the overfitting problem effectively.
Abstract:Localization of a target object has been performed conventionally using multiple terrestrial reference nodes. This paradigm is recently shifted towards utilization of unmanned aerial vehicles (UAVs) for locating target objects. Since locating of a target using simultaneous multiple UAVs is costly and impractical, achieving this task by utilizing single UAV becomes desirable. Hence, in this paper, we propose an RSSI-based localization method that utilizes only a single UAV. The proposed approach is based on clustering method along with the Singular Value Decomposition (SVD). The performance of the proposed method is verified by the experimental measurements collected by a UAV that we have designed and computer simulations. The results show that the proposed method can achieve location accuracy as low as 7m depending on the number of iterations.
Abstract:This paper proposes a new 3D Human Action Recognition system as a two-phase system: (1) Deep Metric Learning Module which learns a similarity metric between two 3D joint sequences using Siamese-LSTM networks; (2) A Multiclass Classification Module that uses the output of the first module to produce the final recognition output. This model has several advantages: the first module is trained with a larger set of data because it uses many combinations of sequence pairs.Our deep metric learning module can also be trained independently of the datasets, which makes our system modular and generalizable. We tested the proposed system on standard and newly introduced datasets that showed us that initial results are promising. We will continue developing this system by adding more sophisticated LSTM blocks and by cross-training between different datasets.