With the recent development of autonomous driving technology, as the pursuit of efficiency for repetitive tasks and the value of non-face-to-face services increase, mobile service robots such as delivery robots and serving robots attract attention, and their demands are increasing day by day. However, when something goes wrong, most commercial serving robots need to return to their starting position and orientation to operate normally again. In this paper, we focus on end-to-end relocalization of serving robots to address the problem. It is to predict robot pose directly from only the onboard sensor data using neural networks. In particular, we propose a deep neural network architecture for the relocalization based on camera-2D LiDAR sensor fusion. We call the proposed method FusionLoc. In the proposed method, the multi-head self-attention complements different types of information captured by the two sensors. Our experiments on a dataset collected by a commercial serving robot demonstrate that FusionLoc can provide better performances than previous relocalization methods taking only a single image or a 2D LiDAR point cloud as well as a straightforward fusion method concatenating their features.
相關內容
Besides standard cameras, autonomous vehicles typically include multiple additional sensors, such as lidars and radars, which help acquire richer information for perceiving the content of the driving scene. While several recent works focus on fusing certain pairs of sensors - such as camera with lidar or radar - by using architectural components specific to the examined setting, a generic and modular sensor fusion architecture is missing from the literature. In this work, we propose HRFuser, a modular architecture for multi-modal 2D object detection. It fuses multiple sensors in a multi-resolution fashion and scales to an arbitrary number of input modalities. The design of HRFuser is based on state-of-the-art high-resolution networks for image-only dense prediction and incorporates a novel multi-window cross-attention block as the means to perform fusion of multiple modalities at multiple resolutions. We demonstrate via extensive experiments on nuScenes and the adverse conditions DENSE datasets that our model effectively leverages complementary features from additional modalities, substantially improving upon camera-only performance and consistently outperforming state-of-the-art 3D and 2D fusion methods evaluated on 2D object detection metrics. The source code is publicly available.
Object detection on Lidar point cloud data is a promising technology for autonomous driving and robotics which has seen a significant rise in performance and accuracy during recent years. Particularly uncertainty estimation is a crucial component for down-stream tasks and deep neural networks remain error-prone even for predictions with high confidence. Previously proposed methods for quantifying prediction uncertainty tend to alter the training scheme of the detector or rely on prediction sampling which results in vastly increased inference time. In order to address these two issues, we propose LidarMetaDetect (LMD), a light-weight post-processing scheme for prediction quality estimation. Our method can easily be added to any pre-trained Lidar object detector without altering anything about the base model and is purely based on post-processing, therefore, only leading to a negligible computational overhead. Our experiments show a significant increase of statistical reliability in separating true from false predictions. We propose and evaluate an additional application of our method leading to the detection of annotation errors. Explicit samples and a conservative count of annotation error proposals indicates the viability of our method for large-scale datasets like KITTI and nuScenes. On the widely-used nuScenes test dataset, 43 out of the top 100 proposals of our method indicate, in fact, erroneous annotations.
Monocular visual-inertial odometry (VIO) is a low-cost solution to provide high-accuracy, low-drifting pose estimation. However, it has been meeting challenges in vehicular scenarios due to limited dynamics and lack of stable features. In this paper, we propose Ground-VIO, which utilizes ground features and the specific camera-ground geometry to enhance monocular VIO performance in realistic road environments. In the method, the camera-ground geometry is modeled with vehicle-centered parameters and integrated into an optimization-based VIO framework. These parameters could be calibrated online and simultaneously improve the odometry accuracy by providing stable scale-awareness. Besides, a specially designed visual front-end is developed to stably extract and track ground features via the inverse perspective mapping (IPM) technique. Both simulation tests and real-world experiments are conducted to verify the effectiveness of the proposed method. The results show that our implementation could dramatically improve monocular VIO accuracy in vehicular scenarios, achieving comparable or even better performance than state-of-art stereo VIO solutions. The system could also be used for the auto-calibration of IPM which is widely used in vehicle perception. A toolkit for ground feature processing, together with the experimental datasets, would be made open-source (//github.com/GREAT_WHU/gv_tools).
As artificial intelligence spreads out to numerous fields, the application of AI to sports analytics is also in the spotlight. However, one of the major challenges is the difficulty of automated acquisition of continuous movement data during sports matches. In particular, it is a conundrum to reliably track a tiny ball on a wide soccer pitch with obstacles such as occlusion and imitations. Tackling the problem, this paper proposes an inference framework of ball trajectory from player trajectories as a cost-efficient alternative to ball tracking. We combine Set Transformers to get permutation-invariant and equivariant representations of the multi-agent contexts with a hierarchical architecture that intermediately predicts the player ball possession to support the final trajectory inference. Also, we introduce the reality loss term and postprocessing to secure the estimated trajectories to be physically realistic. The experimental results show that our model provides natural and accurate trajectories as well as admissible player ball possession at the same time. Lastly, we suggest several practical applications of our framework including missing trajectory imputation, semi-automated pass annotation, automated zoom-in for match broadcasting, and calculating possession-wise running performance metrics.
Recent advances in neural implicit fields enables rapidly reconstructing 3D geometry from multi-view images. Beyond that, recovering physical properties such as material and illumination is essential for enabling more applications. This paper presents a new method that effectively learns relightable neural surface using pre-intergrated rendering, which simultaneously learns geometry, material and illumination within the neural implicit field. The key insight of our work is that these properties are closely related to each other, and optimizing them in a collaborative manner would lead to consistent improvements. Specifically, we propose NeuS-PIR, a method that factorizes the radiance field into a spatially varying material field and a differentiable environment cubemap, and jointly learns it with geometry represented by neural surface. Our experiments demonstrate that the proposed method outperforms the state-of-the-art method in both synthetic and real datasets.
Estimating human pose and shape from monocular images is a long-standing problem in computer vision. Since the release of statistical body models, 3D human mesh recovery has been drawing broader attention. With the same goal of obtaining well-aligned and physically plausible mesh results, two paradigms have been developed to overcome challenges in the 2D-to-3D lifting process: i) an optimization-based paradigm, where different data terms and regularization terms are exploited as optimization objectives; and ii) a regression-based paradigm, where deep learning techniques are embraced to solve the problem in an end-to-end fashion. Meanwhile, continuous efforts are devoted to improving the quality of 3D mesh labels for a wide range of datasets. Though remarkable progress has been achieved in the past decade, the task is still challenging due to flexible body motions, diverse appearances, complex environments, and insufficient in-the-wild annotations. To the best of our knowledge, this is the first survey to focus on the task of monocular 3D human mesh recovery. We start with the introduction of body models and then elaborate recovery frameworks and training objectives by providing in-depth analyses of their strengths and weaknesses. We also summarize datasets, evaluation metrics, and benchmark results. Open issues and future directions are discussed in the end, hoping to motivate researchers and facilitate their research in this area. A regularly updated project page can be found at //github.com/tinatiansjz/hmr-survey.
Humans perceive the world by concurrently processing and fusing high-dimensional inputs from multiple modalities such as vision and audio. Machine perception models, in stark contrast, are typically modality-specific and optimised for unimodal benchmarks, and hence late-stage fusion of final representations or predictions from each modality (`late-fusion') is still a dominant paradigm for multimodal video classification. Instead, we introduce a novel transformer based architecture that uses `fusion bottlenecks' for modality fusion at multiple layers. Compared to traditional pairwise self-attention, our model forces information between different modalities to pass through a small number of bottleneck latents, requiring the model to collate and condense the most relevant information in each modality and only share what is necessary. We find that such a strategy improves fusion performance, at the same time reducing computational cost. We conduct thorough ablation studies, and achieve state-of-the-art results on multiple audio-visual classification benchmarks including Audioset, Epic-Kitchens and VGGSound. All code and models will be released.
Point cloud-based large scale place recognition is fundamental for many applications like Simultaneous Localization and Mapping (SLAM). Although many models have been proposed and have achieved good performance by learning short-range local features, long-range contextual properties have often been neglected. Moreover, the model size has also become a bottleneck for their wide applications. To overcome these challenges, we propose a super light-weight network model termed SVT-Net for large scale place recognition. Specifically, on top of the highly efficient 3D Sparse Convolution (SP-Conv), an Atom-based Sparse Voxel Transformer (ASVT) and a Cluster-based Sparse Voxel Transformer (CSVT) are proposed to learn both short-range local features and long-range contextual features in this model. Consisting of ASVT and CSVT, SVT-Net can achieve state-of-the-art on benchmark datasets in terms of both accuracy and speed with a super-light model size (0.9M). Meanwhile, two simplified versions of SVT-Net are introduced, which also achieve state-of-the-art and further reduce the model size to 0.8M and 0.4M respectively.
Multimodal sentiment analysis is a very actively growing field of research. A promising area of opportunity in this field is to improve the multimodal fusion mechanism. We present a novel feature fusion strategy that proceeds in a hierarchical fashion, first fusing the modalities two in two and only then fusing all three modalities. On multimodal sentiment analysis of individual utterances, our strategy outperforms conventional concatenation of features by 1%, which amounts to 5% reduction in error rate. On utterance-level multimodal sentiment analysis of multi-utterance video clips, for which current state-of-the-art techniques incorporate contextual information from other utterances of the same clip, our hierarchical fusion gives up to 2.4% (almost 10% error rate reduction) over currently used concatenation. The implementation of our method is publicly available in the form of open-source code.
In this paper, we propose a novel multi-task learning architecture, which incorporates recent advances in attention mechanisms. Our approach, the Multi-Task Attention Network (MTAN), consists of a single shared network containing a global feature pool, together with task-specific soft-attention modules, which are trainable in an end-to-end manner. These attention modules allow for learning of task-specific features from the global pool, whilst simultaneously allowing for features to be shared across different tasks. The architecture can be built upon any feed-forward neural network, is simple to implement, and is parameter efficient. Experiments on the CityScapes dataset show that our method outperforms several baselines in both single-task and multi-task learning, and is also more robust to the various weighting schemes in the multi-task loss function. We further explore the effectiveness of our method through experiments over a range of task complexities, and show how our method scales well with task complexity compared to baselines.
小貼士
登錄享
相關主題
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191