Current state-of-the-art autonomous driving vehicles mainly rely on each individual sensor system to perform perception tasks. Such a framework’s reliability could be limited by occlusion or sensor failure. To address this issue, more recent research proposes using vehicle-to-vehicle (V2V) communication to share perception information with others. However, most relevant works focus only on cooperative detection and leave cooperative tracking an underexplored research field. A few recent datasets, such as V2V4Real, provide 3D multi-object cooperative tracking benchmarks. However, their proposed methods mainly use cooperative detection results as input to a standard single-sensor Kalman Filter-based tracking algorithm. In their approach, the measurement uncertainty of different sensors from different connected autonomous vehicles (CAVs) may not be properly estimated to utilize the theoretical optimality property of Kalman Filter-based tracking algorithms. In this paper, we propose a novel 3D multi-object cooperative tracking algorithm for autonomous driving via a differentiable multi-sensor Kalman Filter. Our algorithm learns to estimate measurement uncertainty for each detection that can better utilize the theoretical property of Kalman Filter-based tracking methods. The experiment results show that our algorithm improves the tracking accuracy by 17% with only 0.037x communication costs compared with the state-of-the-art method in V2V4Real. Our code and videos are available at the URL and the URL.

Multi-object tracking is an important ability for an autonomous vehicle to safely navigate a traffic scene. Current state-of-the-art follows the tracking-by-detection paradigm where existing tracks are associated with detected objects through some distance metric. Key challenges to increase tracking accuracy lie in data association and track life cycle management. We propose a probabilistic, multi-modal, multiobject tracking system consisting of different trainable modules to provide robust and data-driven tracking results. First, we learn how to fuse features from 2D images and 3D LiDAR point clouds to capture the appearance and geometric information of an object. Second, we propose to learn a metric that combines the Mahalanobis and feature distances when comparing a track and a new detection in data association. And third, we propose to learn when to initialize a track from an unmatched object detection. Through extensive quantitative and qualitative results, we show that when using the same object detectors our method outperforms state-of-the-art approaches on the NuScenes and KITTI datasets.

Modeling and prediction of human motion dynamics has long been a challenging problem in computer vision, and most existing methods rely on the end-to-end supervised training of various architectures of recurrent neural networks. Inspired by the recent success of deep reinforcement learning methods, in this paper we propose a new reinforcement learning formulation for the problem of human pose prediction, and develop an imitation learning algorithm for predicting future poses under this formulation through a combination of behavioral cloning and generative adversarial imitation learning. Our experiments show that our proposed method outperforms all existing state-of-the-art baseline models by large margins on the task of human pose prediction in both short-term predictions and long-term predictions, while also enjoying huge advantage in training speed.

Forecasting human dynamics is a very interesting but challenging task with several prospective applications in robotics, health-care, among others. Researchers have recently developed methods for human pose forecasting; but unfortunately, they often introduce a number of simplification assumptions. For instance, previous work either focuses only on short-term or long-term predictions, while sacrificing one or the other. Furthermore, they use the activity labels as part of the training process and require them to be available at testing time. These simplifications limit the usage of such pose forecasting models for real-world applications. To overcome these limitations, we propose a new action-agnostic method for short-and long-term human pose forecasting. Our triangular-prism recurrent neural network (TP-RNN) models the hierarchical and multi-scale characteristics of human dynamics. Our model captures the latent hierarchical structure in human pose sequences by encoding temporal dependencies with different time-scales. We run an extensive set of experiments on Human 3.6M and Penn Action datasets and show that our method outperforms baseline and state-of-the-art methods quantitatively and qualitatively. Code is available at https://github.com/eddyhkchiu/pose_forecast_wacv/.

Stroke is the third leading cause of death and the principal cause of serious long-term disability in the United States. Accurate prediction of stroke is highly valuable for early intervention and treatment. In this study, we compare the Cox proportional hazards model with a machine learning approach for stroke prediction on the Cardiovascular Health Study (CHS) dataset. Specifically, we consider the common problems of data imputation, feature selection, and prediction in medical datasets. We propose a novel automatic feature selection algorithm that selects robust features based on our proposed heuristic: conservative mean. Combined with Support Vector Machines (SVMs), our proposed feature selection algorithm achieves a greater area under the ROC curve (AUC) as compared to the Cox proportional hazards model and L1 regularized Cox feature selection algorithm. Furthermore, we present a margin-based censored regression algorithm that combines the concept of margin-based classifiers with censored regression to achieve a better concordance index than the Cox model. Overall, our approach outperforms the current state-of-the-art in both metrics of AUC and concordance index. In addition, our work has also identified potential risk factors that have not been discovered by traditional approaches. Our method can be applied to clinical prediction of other diseases, where missing data are common and risk factors are not well understood.

3D TV will become a prominent technology in the next generation. In this paper, a depth image based rendering system is proposed from algorithm level to hardware architecture level. We propose a novel depth image based rendering algorithm with edge-dependent Gaussian filter and interpolation to improve the rendered stereo image quality. Based on our proposed algorithm, a fully-pipelined depth image based rendering hardware accelerator is proposed to support real-time rendering. The proposed hardware accelerator is optimized in three steps. First, we analyze the effect of fixed point operation and choose the optimal wordlength to keep the stereo image quality. Second, a three-parallel edge-dependent Gaussian filter architecture is proposed to solve the critical problem of memory bandwidth. Finally, we optimize the hardware cost by the proposed hardware architecture. Only 1/21 amounts of vertical PEs and 1/11 amounts of horizontal PEs is needed by the proposed folded edge-dependent Gaussian filter architecture. Furthermore, by the proposed check mode, the whole Z-buffer can be eliminated during 3D image warping. In additions, the on-chip SRAMs can be reduced to 66.7 percent compared with direct implementation by global and local disparity separation scheme. A prototype chip can achieve real-time requirement under the operating frequency of 80 MHz for 25 SDTV frames per second (fps) in left and right channel simultaneously. The simulation result also shows the hardware cost is quite small compared with the conventional rendering architecture