Long-term object detection requires the integration of frame-based results over several seconds. For non-deformable objects, long-term detection is often addressed using object detection followed by video tracking. Unfortunately, tracking is inapplicable to objects that undergo dramatic changes in appearance from frame to frame. As a related example, we study hand detection over long video recordings in collaborative learning environments. More specifically, we develop long-term hand detection methods that can deal with partial occlusions and dramatic changes in appearance.
Our approach integrates object-detection, followed by time projections, clustering, and small region removal to provide effective hand detection over long videos. The hand detector achieved average precision (AP) of 72% at 0.5 intersection over union (IoU). The detection results were improved to 81% by using our optimized approach for data augmentation. The method runs at 4.7× the real-time with AP of 81% at 0.5 intersection over the union. Our method reduced the number of false-positive hand detections by 80% by improving IoU ratios from 0.2 to 0.5. The overall hand detection system runs at 4× real-time.
more »
« less
Revisiting Jump-Diffusion Process for Visual Tracking: A Reinforcement Learning Approach
In this work, we revisit the classical stochastic jump-diffusion process and develop an effective variant for estimating visibility statuses of objects while tracking them in videos. Dealing with partial or full occlusions is a long standing problem in computer vision but largely remains unsolved. In this work, we cast the above problem as a Markov Decision Process and develop a policy-based jump-diffusion method to jointly track object locations in videos and estimate their visibility statuses. Our method employs a set of jump dynamics to change object’s visibility statuses and a set of diffusion dynamics to track objects in videos. Different from traditional jump-diffusion process that stochastically generates dynamics, we utilize deep policy functions to determine the best dynamic for the present state and learn the optimal policies using reinforcement learning methods. Our method is capable of tracking objects with full or partial occlusions in crowded scenes. We evaluate the proposed method over challenging video sequences and compare it to alternative tracking methods. Significant improvements are made particularly for videos with frequent interactions or occlusions.
more »
« less
- Award ID(s):
- 1657600
- PAR ID:
- 10093230
- Date Published:
- Journal Name:
- IEEE Transactions on Circuits and Systems for Video Technology
- ISSN:
- 1051-8215
- Page Range / eLocation ID:
- 1 to 1
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Tracking humans that are interacting with the other subjects or environment remains unsolved in visual tracking, because the visibility of the human of interests in videos is unknown and might vary over time. In particular, it is still difficult for state-of-the-art human trackers to recover completely human trajectories in crowded scenes with frequent human interactions. In this work, we consider the visibility status of a subject as a fluent variable, whose change is mostly attributed to the subject’s interaction with the surrounding, e.g., crossing behind another object, entering a a building, or getting into a vehicle, etc. We introduce a Causal And-Or Graph (C-AOG) to represent the causal effect relations between an object’s visibility fluent and its activities, and develop a probabilistic graph model to jointly reason the visibility fluent change (e.g., from visible to invisible) and track humans in videos. We formulate this joint task as an iterative search of a feasible causal graph structure that enables fast search algorithm, e.g., dynamic programming method. We apply the proposed method to challenging video sequences to evaluate its capabilities of estimating visibility fluent changes of subjects and tracking subjects of interests over time. Results with comparisons demonstrate that our method outperforms the alternative trackers and can recover complete trajectories of humans in complicated scenarios with frequent human interactionsmore » « less
-
The paper develops datasets and methods to assess student participation in real-life collaborative learning environments. In collaborative learning environments, students are organized into small groups where they are free to interact within their group. Thus, students can move around freely causing issues with strong pose variation, move out and re-enter the camera scene, or face away from the camera. We formulate the problem of assessing student participation into two subproblems: (i) student group detection against strong background interference from other groups, and (ii) dynamic participant tracking within the group. A massive independent testing dataset of 12,518,250 student label instances, of total duration of 21 hours and 22 minutes of real-life videos, is used for evaluating the performance of our proposed method for student group detection. The proposed method of using multiple image representations is shown to perform equally or better than YOLO on all video instances. Over the entire dataset, the proposed method achieved an F1 score of 0.85 compared to 0.80 for YOLO. Following student group detection, the paper presents the development of a dynamic participant tracking system for assessing student group participation through long video sessions. The proposed dynamic participant tracking system is shown to perform exceptionally well, missing a student in just one out of 35 testing videos. In comparison, a stateof- the-art method fails to track students in 14 out of the 35 testing videos. The proposed method achieves 82.3% accuracy on an independent set of long, real-life collaborative videos.more » « less
-
Many robot tasks may involve achieving visibility (such as to observe areas of interest) or maintaining occlusion (such as to avoid disturbing other agents). We generally formulate such sequential visibility tasks for 3D worlds, termed the Park Rangers’ Problem, and we develop an approach to solve such tasks offering completeness under certain requirements. Our approach constructs an abstraction based on an exact test for visibility between areas, and multiple tests and relaxations for the nonconvex problem of determining occlusions between areas. We apply a constraint-based planning approach and iteratively refine the abstraction. Finally, we evaluate the approach on simulated visibility scenarios.more » « less
-
In recent years, satellites capable of capturing videos have been developed and launched to provide high definition satellite videos that enable applications far beyond the capabilities of remotely sensed imagery. Moving object detection and moving object tracking are among the most essential and challenging tasks, but existing studies have mainly focused on vehicles. To accurately detect and then track more complex moving objects, specifically airplanes, we need to address the challenges posed by the new data. First, slow-moving airplanes may cause foreground aperture problem during detection. Second, various disturbances, especially parallax motion, may cause false detection. Third, airplanes may perform complex motions, which requires a rotation-invariant and scale-invariant tracking algorithm. To tackle these difficulties, we first develop an Improved Gaussian-based Background Subtractor (IPGBBS) algorithm for moving airplane detection. This algorithm adopts a novel strategy for background and foreground adaptation, which can effectively deal with the foreground aperture problem. Then, the detected moving airplanes are tracked by a Primary Scale Invariant Feature Transform (P-SIFT) keypoint matching algorithm. The P-SIFT keypoint of an airplane exhibits high distinctiveness and repeatability. More importantly, it provides a highly rotation-invariant and scale-invariant feature vector that can be used in the matching process to determine the new locations of the airplane in the frame sequence. The method was tested on a satellite video with eight moving airplanes. Compared with state-of-the-art algorithms, our IPGBBS algorithm achieved the best detection accuracy with the highest F1 score of 0.94 and also demonstrated its superiority on parallax motion suppression. The P-SIFT keypoint matching algorithm could successfully track seven out of the eight airplanes. Based on the tracking results, movement trajectories of the airplanes and their dynamic properties were also estimated.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Journal Article:
- https://doi.org/10.1109/TCSVT.2018.2862891
