Action spotting is an important element of general activity understanding. It consists of detecting human-induced events annotated with single timestamps. In this paper, we propose a novel loss function for action spotting. Our loss aims at dealing specifically with the temporal context naturally present around an action. Rather than focusing on the single annotated frame of the action to spot, we consider different temporal segments surrounding it and shape our loss function accordingly. We test our loss on SoccerNet, a large dataset of soccer videos, showing an improvement of 12.8% on the current baseline. We also show the generalization capability of our loss function on ActivityNet for activity proposals and detection, by spotting the beginning and the end of each activity. Furthermore, we provide an extended ablation study and identify challenging cases for action spotting in soccer videos. Finally, we qualitatively illustrate how our loss induces a precise temporal understanding of actions, and how such semantic knowledge can be leveraged to design a highlights generator.
In autonomous driving pipelines, perception modules provide a visual understanding of the surrounding road scene. Among the perception tasks, vehicle detection is of paramount importance for a safe driving as it identifies the position of other agents sharing the road. In our work, we propose PointRGCN: a graph-based 3D object detection pipeline based on graph convolutional networks (GCNs) which operates exclusively on 3D LiDAR point clouds. To perform more accurate 3D object detection, we leverage a graph representation that performs proposal feature and context aggregation. We integrate residual GCNs in a two-stage 3D object detection pipeline, where 3D object proposals are refined using a novel graph representation. In particular, R-GCN is a residual GCN that classifies and regresses 3D proposals, and C-GCN is a contextual GCN that further refines proposals by sharing contextual information between multiple proposals. We integrate our refinement modules into a novel 3D detection pipeline, PointRGCN, and achieve state-of-the-art performance on the easy difficulty for the bird eye view detection task.
Point clouds are challenging to process due to their sparsity, therefore autonomous vehicles rely more on appearance attributes than pure geometric features. However, 3D LIDAR perception can provide crucial information for urban navigation in challenging light or weather conditions. In this paper, we investigate the versatility of Shape Completion for 3D Object Tracking in LIDAR point clouds. We design a Siamese tracker that encodes model and candidate shapes into a compact latent representation. We regularize the encoding by enforcing the latent representation to decode into an object model shape. We observe that 3D object tracking and 3D shape completion complement each other. Learning a more meaningful latent representation shows better discriminatory capabilities, leading to improved tracking performance. We test our method on the KITTI Tracking set using car 3D bounding boxes. Our model reaches a 76.94% Success rate and 81.38% Precision for 3D Object Tracking, with the shape completion regularization leading to an improvement of 3% in both metrics.
Tracking vehicles in LIDAR point clouds is a challenging task due to the sparsity of the data and the dense search space. The lack of structure in point clouds impedes the use of convolution and correlation filters usually employed in 2D object tracking. In addition, structuring point clouds is cumbersome and implies losing fine-grained information. As a result, generating proposals in 3D space is expensive and inefficient. In this paper, we leverage the dense and structured Bird Eye View (BEV) representation of LIDAR point clouds to efficiently search for objects of interest. We use an efficient Region Proposal Network and generate a small number of object proposals in 3D. Successively, we refine our selection of 3D object candidates by exploiting the similarity capability of a 3D Siamese network. We regularize the latter 3D Siamese network for shape completion to enhance its discrimination capability. Our method attempts to solve both for an efficient search space in the BEV space and a meaningful selection using 3D LIDAR point cloud. We show that the Region Proposal in the BEV outperforms Bayesian methods such as Kalman and Particle Filters in providing proposal by a significant margin and that such candidates are suitable for the 3D Siamese network. By training our method end-to-end, we outperform the previous baseline in vehicle tracking by 12% / 18% in Success and Precision when using only 16 candidates.
In this paper, we show how absolute orientation measurements provided by low-cost but high-fidelity IMU sensors can be integrated into the KinectFusion pipeline. We show that integration improves both runtime, robustness and quality of the 3D reconstruction. In particular, we use this orientation data to seed and regularize the ICP registration technique. We also present a technique to filter the pairs of 3D matched points based on the distribution of their distances. This filter is implemented efficiently on the GPU. Estimating the distribution of the distances helps control the number of iterations necessary for the convergence of the ICP algorithm. Finally, we show experimental results that highlight improvements in robustness, a speed-up of almost 12%, and a gain in tracking quality of 53% for the ATE metric on the Freiburg benchmark.
In this paper, we introduce SoccerNet, a benchmark for action spotting in soccer videos. The dataset is composed of 500 complete soccer games from six main European leagues, covering three seasons from 2014 to 2017 and a total duration of 764 hours. A total of 6,637 temporal annotations are automatically parsed from online match reports at a one minute resolution for three main classes of events (Goal, Yellow/Red Card, and Substitution). As such, the dataset is easily scalable. These annotations are manually refined to a one second resolution by anchoring them at a single timestamp following well-defined soccer rules. With an average of one event every 6.9 minutes, this dataset focuses on the problem of localizing very sparse events within long videos. We define the task of spotting as finding the anchors of soccer events in a video. Making use of recent developments in the realm of generic action recognition and detection in video, we provide strong baselines for detecting soccer events. We show that our best model for classifying temporal segments of length one minute reaches a mean Average Precision (mAP) of 67.8%. For the spotting task, our baseline reaches an Average-mAP of 49.7% for tolerances $\delta$ ranging from 5 to 60 seconds. Our dataset and models are available at https://silviogiancola.github.io/SoccerNet.
Despite the numerous developments in object tracking, further development of current tracking algorithms is limited by small and mostly saturated datasets. As a matter of fact, data-hungry trackers based on deep-learning currently rely on object detection datasets due to the scarcity of dedicated large-scale tracking datasets. In this work, we present TrackingNet, the first large-scale dataset and benchmark for object tracking in the wild. We provide more than 30K videos with more than 14 million dense bounding box annotations. Our dataset covers a wide selection of object classes in broad and diverse context. By releasing such a large-scale dataset, we expect deep trackers to further improve and generalize. In addition, we introduce a new benchmark composed of 500 novel videos, modeled with a distribution similar to our training dataset. By sequestering the annotation of the test set and providing an online evaluation server, we provide a fair benchmark for future development of object trackers. Deep trackers fine-tuned on a fraction of our dataset improve their performance by up to 1.6% on OTB100 and up to 1.7% on TrackingNet Test. We provide an extensive benchmark on TrackingNet by evaluating more than 20 trackers. Our results suggest that object tracking in the wild is far from being solved.
In this work, we propose a method for three-dimensional (3D) reconstruction of wide crime scene, based on a Simultaneous Localization and Mapping (SLAM) approach. We used a Kinect V2 Time-of-Flight (TOF) RGB-D camera to provide colored dense point clouds at a 30 Hz frequency. This device is moved freely (6 degrees of freedom) during the scene exploration. The implemented SLAM solution aligns successive point clouds using an 3D keypoints description and matching approach. This type of approach exploits both colorimetric and geometrical information, and permits reconstruction under poor illumination conditions. Our solution has been tested for indoor crime scene and outdoor archaeological site reconstruction, returning a mean error around one centimeter. It is less precise than environmental laser scanner solution, but more practical and portable as well as less cumbersome. Also, the hardware is definitively cheaper.