The evolution of Advanced Driver Assistance Systems (ADAS) has increased the need for robust and generalizable algorithms for multi-object tracking. Traditional statistical model-based tracking methods rely on predefined motion models and assumptions about system noise distributions. Although computationally efficient, they often lack adaptability to varying traffic scenarios and require extensive manual design and parameter tuning. To address these issues, we propose a novel 3D multi-object tracking approach for vehicles, HybridTrack, which integrates a data-driven Kalman Filter (KF) within a tracking-by-detection paradigm. In particular, it learns the transition residual and Kalman gain directly from data, which eliminates the need for manual motion and stochastic parameter modeling. Validated on the real-world KITTI dataset, HybridTrack achieves 82.72% HOTA accuracy, significantly outperforming state-of-the-art methods. We also evaluate our method under different configurations, achieving the fastest processing speed of 112 FPS. Consequently, HybridTrack eliminates the dependency on scene-specific designs while improving performance and maintaining real-time efficiency.
In recent years, Vehicle Make and Model Recognition (VMMR) has attracted a lot of attention as it plays a crucial role in Intelligent Transportation Systems (ITS). Accurate and efficient VMMR systems are required in real-world applications including intelligent surveillance and autonomous driving. The paper introduces a new large-scale dataset and a novel deep learning paradigm for VMMR. A new large-scale dataset dubbed Diverse large-scale VMM (DVMM) is proposed collecting image-samples with the most popular vehicle brands operating in Europe. A novel VMMR framework is proposed which follows a two-branch architecture performing make and model recognition respectively. A two-stage training procedure and a novel decision module are proposed to process the make and model predictions and compute the final model prediction. In addition, a novel metric based on the true positive rate is proposed to compare classification confusion of the proposed 2B–2S and the baseline methods. A complex experimental validation is carried out, demonstrating the generality, diversity, and practicality of the proposed DVMM dataset. The experimental results show that the proposed framework provides accuracy over the more diverse DVMM dataset and accuracy over traditional VMMR datasets. The proposed two-branch approach outperforms the conventional one-branch approach for VMMR over small-, medium-, and large-scale datasets by providing lower vehicle model confusion and reduced inter-make ambiguity. The paper demonstrates the advantages of the proposed two-branch VMMR paradigm in terms of robustness and lower confusion relative to single-branch designs.
21 February 2024 in IEEE Transactions on Instrumentation and Measurement
Synthetic traffic datasets provide highly accurate and affordable annotations, which are of crucial importance in complex vision-based perception tasks performed on real-world traffic data. Due to the lack of paired 2D-3D data, it remains very challenging when adapting the knowledge of a vehicle’s pose in SE (3) with its known 3D geometry. In this paper, we firstly propose a synthetic dataset, SynthV6D, enabling 6D pose estimation of vehicles in monocular traffic images. The dataset comprises industrial-grade vehicles in motion evolving in realistic virtual scenery, covering a wide range of viewpoints and distances. Secondly, we introduce a weakly-supervised domain adaptation approach, dubbed W6DNet, to recover the 6D pose. To this end, by using the synthetic dataset, a novel linked image feature space-based domain adaptation is introduced. Furthermore, an original two-step Double-Fusion block is proposed to fuse the multi-modal data representations and the cross-space features. Consequently, the proposed method learns the pose-specific embeddings. We evaluate W6DNet on the real-world ApolloCar3D dataset. Extensive experimental results demonstrate that, when a small amount of real-world data is accessible, the proposed approach can significantly advance the performance when adapting knowledge from SynthV6D. Moreover, it achieves competitive performance compared to fully supervised state-of-the-art methods.
This paper presents DeepKalPose, a novel approach for enhancing temporal consistency in monocular vehicle pose estimation applied on video through a deep‐learning‐based Kalman filter. By integrating a bi‐directional Kalman filter strategy utilizing forward and backward time‐series processing, combined with a learnable motion model to represent complex motion patterns, the method significantly improves pose accuracy and robustness across various conditions, particularly for occluded or distant vehicles. Experimental validation on the KITTI dataset confirms that DeepKalPose outperforms existing methods in both pose accuracy and temporal consistency.
Since the introduction of the self-attention mechanism and the adoption of the Transformer architecture for Computer Vision tasks, the Vision Transformer-based architectures gained a lot of popularity in the field, being used for tasks such as image classification, object detection and image segmentation. However, efficiently leveraging the attention mechanism in vision transformers for the Monocular 3D Object Detection task remains an open question. In this paper, we present LAM3D, a framework that Leverages self-Attention mechanism for Monocular 3D object Detection. To do so, the proposed method is built upon a Pyramid Vision Transformer v2 (PVTv2) as feature extraction backbone and 2D/3D detection machinery. We evaluate the proposed method on the KITTI 3D Object Detection Benchmark, proving the applicability of the proposed solution in the autonomous driving domain and outperforming reference methods. Moreover, due to the usage of self-attention, LAM3D is able to systematically outperform the equivalent architecture that does not employ self-attention.