In recent years, great progress has been made in the Lift-Splat-Shot-based (LSS-based) 3D object detection method, which converts features of 2D camera view and 3D lidar view to Bird's-Eye-View (BEV) for feature fusion. However, inaccurate depth estimation (e.g. the 'depth jump' problem) is an obstacle to develop LSS-based methods. To alleviate the 'depth jump' problem, we proposed Edge-Aware Bird's-Eye-View (EA-BEV) projector. By coupling proposed edge-aware depth fusion module and depth estimate module, the proposed EA-BEV projector solves the problem and enforces refined supervision on depth. Besides, we propose sparse depth supervision and gradient edge depth supervision, for constraining learning on global depth and local marginal depth information. Our EA-BEV projector is a plug-and-play module for any LSS-based 3D object detection models, and effectively improves the baseline performance. We demonstrate the effectiveness on the nuScenes benchmark. On the nuScenes 3D object detection validation dataset, our proposed EA-BEV projector can boost several state-of-the-art LLS-based baselines on nuScenes 3D object detection benchmark and nuScenes BEV map segmentation benchmark with negligible increment of inference time.
相關內容
Evaluating simultaneous localization and mapping (SLAM) algorithms necessitates high-precision and dense ground truth (GT) trajectories. But obtaining desirable GT trajectories is sometimes challenging without GT tracking sensors. As an alternative, in this paper, we propose a novel prior-assisted SLAM system to generate a full six-degree-of-freedom ($6$-DOF) trajectory at around $10$Hz for benchmarking under the framework of the factor graph. Our degeneracy-aware map factor utilizes a prior point cloud map and LiDAR frame for point-to-plane optimization, simultaneously detecting degeneration cases to reduce drift and enhancing the consistency of pose estimation. Our system is seamlessly integrated with cutting-edge odometry via a loosely coupled scheme to generate high-rate and precise trajectories. Moreover, we propose a norm-constrained gravity factor for stationary cases, optimizing pose and gravity to boost performance. Extensive evaluations demonstrate our algorithm's superiority over existing SLAM or map-based methods in diverse scenarios in terms of precision, smoothness, and robustness. Our approach substantially advances reliable and accurate SLAM evaluation methods, fostering progress in robotics research.
Text-driven diffusion models have unlocked unprecedented abilities in image generation, whereas their video counterpart still lags behind due to the excessive training cost of temporal modeling. Besides the training burden, the generated videos also suffer from appearance inconsistency and structural flickers, especially in long video synthesis. To address these challenges, we design a \emph{training-free} framework called \textbf{ControlVideo} to enable natural and efficient text-to-video generation. ControlVideo, adapted from ControlNet, leverages coarsely structural consistency from input motion sequences, and introduces three modules to improve video generation. Firstly, to ensure appearance coherence between frames, ControlVideo adds fully cross-frame interaction in self-attention modules. Secondly, to mitigate the flicker effect, it introduces an interleaved-frame smoother that employs frame interpolation on alternated frames. Finally, to produce long videos efficiently, it utilizes a hierarchical sampler that separately synthesizes each short clip with holistic coherency. Empowered with these modules, ControlVideo outperforms the state-of-the-arts on extensive motion-prompt pairs quantitatively and qualitatively. Notably, thanks to the efficient designs, it generates both short and long videos within several minutes using one NVIDIA 2080Ti. Code is available at //github.com/YBYBZhang/ControlVideo.
Multispectral methods have gained considerable attention due to their promising performance across various fields. However, most existing methods cannot effectively utilize information from two modalities while optimizing time efficiency. These methods often prioritize accuracy or time efficiency, leaving room for improvement in their performance. To this end, we propose a new method bright channel prior attention for enhancing pedestrian detection in low-light conditions by integrating image enhancement and detection within a unified framework. The method uses the V-channel of the HSV image of the thermal image as an attention map to trigger the unsupervised auto-encoder for visible light images, which gradually emphasizes pedestrian features across layers. Moreover, we utilize unsupervised bright channel prior algorithms to address light compensation in low light images. The proposed method includes a self-attention enhancement module and a detection module, which work together to improve object detection. An initial illumination map is estimated using the BCP, guiding the learning of the self-attention map from the enhancement network to obtain more informative representation focused on pedestrians. The extensive experiments show effectiveness of the proposed method is demonstrated through.
With the prosperity of the video surveillance, multiple visual sensors have been applied for an accurate localization of pedestrians in a specific area, which facilitate various applications like intelligent safety or new retailing. However, previous methods rely on the supervision from the human annotated pedestrian positions in every video frame and camera view, which is a heavy burden in addition to the necessary camera calibration and synchronization. Therefore, we propose in this paper an Unsupervised Multi-view Pedestrian Detection approach (UMPD) to eliminate the need of annotations to learn a multi-view pedestrian detector. 1) Firstly, Semantic-aware Iterative Segmentation (SIS) is proposed to extract discriminative visual representations of the input images from different camera views via an unsupervised pretrained model, then convert them into 2D segments of pedestrians, based on our proposed iterative Principal Component Analysis and the zero-shot semantic classes from the vision-language pretrained models. 2) Secondly, we propose Vertical-aware Differential Rendering (VDR) to not only learn the densities and colors of 3D voxels by the masks of SIS, images and camera poses, but also constraint the voxels to be vertical towards the ground plane, following the physical characteristics of pedestrians. 3) Thirdly, the densities of 3D voxels learned by VDR are projected onto Bird-Eyes-View as the final detection results. Extensive experiments on popular multi-view pedestrian detection benchmarks, i.e., Wildtrack and MultiviewX, show that our proposed UMPD approach, as the first unsupervised method to our best knowledge, performs competitively with the previous state-of-the-art supervised techniques. Code will be available.
This paper addresses video anomaly detection problem for videosurveillance. Due to the inherent rarity and heterogeneity of abnormal events, the problem is viewed as a normality modeling strategy, in which our model learns object-centric normal patterns without seeing anomalous samples during training. The main contributions consist in coupling pretrained object-level action features prototypes with a cosine distance-based anomaly estimation function, therefore extending previous methods by introducing additional constraints to the mainstream reconstruction-based strategy. Our framework leverages both appearance and motion information to learn object-level behavior and captures prototypical patterns within a memory module. Experiments on several well-known datasets demonstrate the effectiveness of our method as it outperforms current state-of-the-art on most relevant spatio-temporal evaluation metrics.
Future sixth-generation (6G) networks are envisioned to provide both sensing and communications functionalities by using densely deployed base stations (BSs) with massive antennas operating in millimeter wave (mmWave) and terahertz (THz). Due to the large number of antennas and the high frequency band, the sensing and communications will operate within the near-field region, thus making the conventional designs based on the far-field channel models inapplicable. This paper studies a near-field multiple-input-multiple-output (MIMO) radar sensing system, in which the transceivers with massive antennas aim to localize multiple near-field targets in the three-dimensional (3D) space. In particular, we adopt a general wavefront propagation model by considering the exact spherical wavefront with both channel phase and amplitude variations over different antennas. Besides, we consider the general transmit signal waveforms and also consider the unknown cluttered environments. Under this setup, the unknown parameters to estimate include the 3D coordinates and the complex reflection coefficients of the multiple targets, as well as the noise and interference covariance matrix. Accordingly, we derive the Cram\'er-Rao bound (CRB) for estimating the target coordinates and reflection coefficients. Next, to facilitate practical localization, we propose an efficient estimator based on the 3D approximate cyclic optimization (3D-ACO), which is obtained following the maximum likelihood (ML) criterion. Finally, numerical results show that considering the exact antenna-varying channel amplitudes achieves more accurate CRB as compared to prior works based on constant channel amplitudes across antennas, especially when the targets are close to the transceivers. It is also shown that the proposed estimator achieves localization performance close to the derived CRB, thus validating its superior performance.
3D object detection plays a crucial role in numerous intelligent vision systems. Detection in the open world inevitably encounters various adverse scenes, such as dense fog, heavy rain, and low light conditions. Although existing efforts primarily focus on diversifying network architecture or training schemes, resulting in significant progress in 3D object detection, most of these learnable modules fail in adverse scenes, thereby hindering detection performance. To address this issue, this paper proposes a monocular 3D detection model designed to perceive twin depth in adverse scenes, termed MonoTDP, which effectively mitigates the degradation of detection performance in various harsh environments. Specifically, we first introduce an adaptive learning strategy to aid the model in handling uncontrollable weather conditions, significantly resisting degradation caused by various degrading factors. Then, to address the depth/content loss in adverse regions, we propose a novel twin depth perception module that simultaneously estimates scene and object depth, enabling the integration of scene-level features and object-level features. Additionally, we assemble a new adverse 3D object detection dataset encompassing a wide range of challenging scenes, including rainy, foggy, and low light weather conditions, with each type of scene containing 7,481 images. Experimental results demonstrate that our proposed method outperforms current state-of-the-art approaches by an average of 3.12% in terms of AP_R40 for car category across various adverse environments.
Knowledge Distillation (KD) is a widely-used technology to inherit information from cumbersome teacher models to compact student models, consequently realizing model compression and acceleration. Compared with image classification, object detection is a more complex task, and designing specific KD methods for object detection is non-trivial. In this work, we elaborately study the behaviour difference between the teacher and student detection models, and obtain two intriguing observations: First, the teacher and student rank their detected candidate boxes quite differently, which results in their precision discrepancy. Second, there is a considerable gap between the feature response differences and prediction differences between teacher and student, indicating that equally imitating all the feature maps of the teacher is the sub-optimal choice for improving the student's accuracy. Based on the two observations, we propose Rank Mimicking (RM) and Prediction-guided Feature Imitation (PFI) for distilling one-stage detectors, respectively. RM takes the rank of candidate boxes from teachers as a new form of knowledge to distill, which consistently outperforms the traditional soft label distillation. PFI attempts to correlate feature differences with prediction differences, making feature imitation directly help to improve the student's accuracy. On MS COCO and PASCAL VOC benchmarks, extensive experiments are conducted on various detectors with different backbones to validate the effectiveness of our method. Specifically, RetinaNet with ResNet50 achieves 40.4% mAP in MS COCO, which is 3.5% higher than its baseline, and also outperforms previous KD methods.
Autonomous driving is regarded as one of the most promising remedies to shield human beings from severe crashes. To this end, 3D object detection serves as the core basis of such perception system especially for the sake of path planning, motion prediction, collision avoidance, etc. Generally, stereo or monocular images with corresponding 3D point clouds are already standard layout for 3D object detection, out of which point clouds are increasingly prevalent with accurate depth information being provided. Despite existing efforts, 3D object detection on point clouds is still in its infancy due to high sparseness and irregularity of point clouds by nature, misalignment view between camera view and LiDAR bird's eye of view for modality synergies, occlusions and scale variations at long distances, etc. Recently, profound progress has been made in 3D object detection, with a large body of literature being investigated to address this vision task. As such, we present a comprehensive review of the latest progress in this field covering all the main topics including sensors, fundamentals, and the recent state-of-the-art detection methods with their pros and cons. Furthermore, we introduce metrics and provide quantitative comparisons on popular public datasets. The avenues for future work are going to be judiciously identified after an in-deep analysis of the surveyed works. Finally, we conclude this paper.
Conventionally, spatiotemporal modeling network and its complexity are the two most concentrated research topics in video action recognition. Existing state-of-the-art methods have achieved excellent accuracy regardless of the complexity meanwhile efficient spatiotemporal modeling solutions are slightly inferior in performance. In this paper, we attempt to acquire both efficiency and effectiveness simultaneously. First of all, besides traditionally treating H x W x T video frames as space-time signal (viewing from the Height-Width spatial plane), we propose to also model video from the other two Height-Time and Width-Time planes, to capture the dynamics of video thoroughly. Secondly, our model is designed based on 2D CNN backbones and model complexity is well kept in mind by design. Specifically, we introduce a novel multi-view fusion (MVF) module to exploit video dynamics using separable convolution for efficiency. It is a plug-and-play module and can be inserted into off-the-shelf 2D CNNs to form a simple yet effective model called MVFNet. Moreover, MVFNet can be thought of as a generalized video modeling framework and it can specialize to be existing methods such as C2D, SlowOnly, and TSM under different settings. Extensive experiments are conducted on popular benchmarks (i.e., Something-Something V1 & V2, Kinetics, UCF-101, and HMDB-51) to show its superiority. The proposed MVFNet can achieve state-of-the-art performance with 2D CNN's complexity.
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191