Abstract. This paper presents a new algorithm to track a high number of points in a video sequence in real-time. We propose a fast keypoint detector, used to create new particles, and an associated multiscale descriptor (feature) used to match the particles from one frame to the next. The tracking algorithm updates for each particle a series of appearance and kinematic states, that are temporally filtered. It is robust to hand held camera accelerations thanks to a coarse-to-fine dominant movement estimation. Each step is designed to reach the maximal level of data parallelism, to target the most common parallel platforms. Using graphics processing unit, our current implementation handles 10 000 points per frame at 55 frames-per-second on 640 × 480 videos.
International audienceA new action model is proposed, by revisiting local binary patterns for dynamic texture models, applied on trajectory beams calculated on the video. The use of semi dense trajectory field allows to dramatically reduce the computation support to essential mo-tion information, while maintaining a large amount of data to ensure robustness of statistical bag of features action models. A new binary pattern, called Spatial Motion Pattern (SMP) is proposed, which captures self similarity of velocity around each tracked point(particle), along its trajectory. This operator highlights the geometric shape of rigid parts of moving objects in a video sequence. SMPs are combined with basic velocity in-formation to form the local action primitives. Then, a global representation of a space × time video block is provided by using hierarchical blockwise histograms, which allows to efficiently represent the action as a whole, while preserving a certain level of spa-tiotemporal relation between the action primitives. Inheriting from the efficiency and the invariance properties of both the semi dense tracker Video extruder and the LBP based representations, the method is designed for the fast computation of action descrip-tors in unconstrained videos. For improving both robustness and computation time in the case of high definition video, we also present an enhanced version of the semi dense tracker based on the so called super particles, which reduces the number of trajectories while improving their length, reliability and spatial distribution
Two crucial aspects of visual point tracking are addressed in this paper. First, the algorithm should track as many points as possible reliably. Second, the computation should be fast enough, which is challenging on low power embedded platforms. We propose a new multi-scale semi dense point tracker called Video Extruder, whose purpose is to fill the gap between short term, dense motion estimation (optical flow) and long term, sparse salient point tracking. This paper presents a new detector, including a new salience function with low computational complexity and a new selection strategy that allows to obtain a large number of keypoints. Its density and reliability in mobile video scenarios are compared with those of FAST detector. Then, a multi-scale prediction and a matching strategy are presented, based on a hybrid regional coarse-to-fine and temporal prediction, which provides robustness to large camera and object accelerations. Filtering and merging strategies are then used to eliminate most of the wrong or useless trajectories. Thanks to its high degree of parallelism, the proposed algorithm extracts beams of trajectories from the video in a very fast way. We compare it with the state-of-the-art pyramidal Lucas Kanade point tracker and show that, in fast mobile video scenarios, it yields similar quality results, while being up to one order of magnitude faster. Three different parallel implementations of this tracker are presented, including multi-core CPU, GPU and ARM SoCs. On a commodity 2010 CPU, it can track 8 500 points in a 640 × 480 video at 150 Hz.
Optical flow computation consists in recovering the apparent motion field between two images with overlapping fields of view. This paper focuses on a subset of optical flow problems, called epipolar flow, where the camera moves inside a scene containing no moving objects. Accurate solutions exist but their high computational complexities make them non suitable for a large panel of real-time applications.We propose a new epipolar flow approach with low computational complexity achieving the best error rate on the non dense KITTI optical flow 2012 benchmark and running 1000× faster than the second ranked approach. On a 4core 3GHz processor, our multi-core implementation computes a semi dense optical flow field of a 450k pixels image in 260ms. It is a significant advance in reducing the running time of accurate optical flow computation.To achieve such results we rely on the epipolar constraints and the local coherence of the optical flow not only to increase accuracy but also to reduce computational complexity.Our contribution is twofold. It is first, the acceleration and the accuracy increase of current RANSAC based visual odometry algorithms via the estimation of a robust sparse flow field, well distributed over the image domain. And then, the estimation of a semi dense flow field leveraging epipolar constraints and a propagation scheme to speedup the estimation and reduce error rates.
Abstract.A new method for action modelling is proposed, which combines the trajectory beam obtained by semi-dense point tracking and a local binary trend description inspired from the Local Binary Patterns (LBP). The semi dense trajectory approach represents a good trade-off between reliability and density of the motion field, whereas the LBP component allows to capture relevant elementary motion elements along each trajectory, which are encoded into mixed descriptors called Motion Trend Patterns (MTP). The combination of those two fast operators allows a real-time, on line computation of the action descriptors, composed of space-time blockwise histograms of MTP values, which are classified using a fast SVM classifier. An encoding scheme is proposed and compared with the state-of-the-art through an evaluation performed on two academic action video datasets.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.