Ju Hong Yoon

Bayesian Multi-object Tracking Using Motion Context from Multiple Objects

Online multi-object tracking with a single moving camera is a challenging problem as the assumptions of 2D conventional motion models (e.g., first or second order models) in the image coordinate no longer hold because of global camera motion. In this paper, we consider motion context from multiple objects which describes the relative movement between objects and construct a Relative Motion Network (RMN) to factor out the effects of unexpected camera motion for robust tracking. The RMN consists of multiple relative motion models that describe spatial relations between objects, thereby facilitating robust prediction and data association for accurate tracking under arbitrary camera movements. The RMN can be incorporated into various multi-object tracking frameworks and we demonstrate its effectiveness with one tracking framework based on a Bayesian filter. Experiments on benchmark datasets show that online multi-object tracking performance can be better achieved by the proposed method.

Online Multi-object Tracking via Structural Constraint Event Aggregation

Multi-object tracking (MOT) becomes more challenging when objects of interest have similar appearances. In that case, the motion cues are particularly useful for discriminating multiple objects. However, for online 2D MOT in scenes acquired from moving cameras, observable motion cues are complicated by global camera movements and thus not always smooth or predictable. To deal with such unexpected camera motion for online 2D MOT, a structural motion constraint between objects has been utilized thanks to its robustness to camera motion. In this paper, we propose a new data association method that effectively exploits structural motion constraints in the presence of large camera motion. In addition, to further improve the robustness of data association against mis-detections and false positives, a novel event aggregation approach is developed to integrate structural constraints in assignment costs for online MOT. Experimental results on a large number of datasets demonstrate the effectiveness of the proposed algorithm for online 2D MOT.

Visual tracking via adaptive tracker selection with multiple features

In this paper, a robust visual tracking method is proposed to track an object in dynamic conditions that include motion blur, illumination changes, pose variations, and occlusions. To cope with these challenges, multiple trackers with different feature descriptors are utilized, and each of which shows different level of robustness to certain changes in an objects appearance. To fuse these independent trackers, we propose two configurations, tracker selection and interaction. The tracker interaction is achieved based on a transition probability matrix (TPM) in a probabilistic manner. The tracker selection extracts one tracking result from among multiple tracker outputs by choosing the tracker that has the highest tracker probability. According to various changes in an objects appearance, the TPM and tracker probability are updated in a recursive Bayesian form by evaluating each trackers reliability, which is measured by a robust tracker likelihood function (TLF). When the tracking in each frame is completed, the estimated objects state is obtained and fed into the reference update via the proposed learning strategy, which retains the robustness and adaptability of the TLF and multiple trackers. The experimental results demonstrate that our proposed method is robust in various benchmark scenarios.

Joint Initialization and Tracking of Multiple Moving Objects Using Doppler Information

In this correspondence, a new multi-target tracking (MTT) algorithm based on the probability hypothesis density (PHD) filtering framework is designed in order to improve tracking performance via the proposal of two contributions. First, unlike typical existing systems, Doppler information is additionally employed to enhance the clutter rejection capability. Specifically, position and Doppler measurements are iteratively incorporated in a two-step process based on a Gaussian mixture PHD (GMPHD) filter. Second, a concrete initialization process is proposed in the birth intensity design of the GMPHD. The initialization process from consecutive measurements leads to a reliable birth intensity that improves track management performance. Both contributions are subsequently evaluated through MTT simulations, the results of which verify that the proposed algorithm is viable.

Interacting Multiview Tracker

A robust algorithm is proposed for tracking a target object in dynamic conditions including motion blurs, illumination changes, pose variations, and occlusions. To cope with these challenging factors, multiple trackers based on different feature representations are integrated within a probabilistic framework. Each view of the proposed multiview (multi-channel) feature learning algorithm is concerned with one particular feature representation of a target object from which a tracker is developed with different levels of reliability. With the multiple trackers, the proposed algorithm exploits tracker interaction and selection for robust tracking performance. In the tracker interaction, a transition probability matrix is used to estimate dependencies between trackers. Multiple trackers communicate with each other by sharing information of sample distributions. The tracker selection process determines the most reliable tracker with the highest probability. To account for object appearance changes, the transition probability matrix and tracker probability are updated in a recursive Bayesian framework by reflecting the tracker reliability measured by a robust tracker likelihood function that learns to account for both transient and stable appearance changes. Experimental results on benchmark datasets demonstrate that the proposed interacting multiview algorithm performs robustly and favorably against state-of-the-art methods in terms of several quantitative metrics.

Fast communication: Efficient importance sampling function design for sequential Monte Carlo PHD filter

In this paper, we propose a novel implementation of the probability hypothesis density (PHD) filter based on the sequential Monte Carlo (SMC) method called SMC-PHD filter. The SMC-PHD filter is analogous to the sequential importance sampling which generates samples using an importance sampling (IS) function. Even though this filter permits general class of IS density function, many previous implementations have simply used the state transition density function. However, this approach leads to a degeneracy problem and renders the filter inefficient. Thus, we propose a novel IS function for the SMC-PHD filter using a combination of an unscented information filter and a gating technique. Further, we use measurement-driven birth target intensities because they are more efficient and accurate than selecting birth targets selected using arbitrary or expected mean target states. The performance of the SMC-PHD filter with the proposed IS function was subsequently evaluated through a simulation and it was shown to outperform the standard SMC-PHD filter and recently proposed auxiliary PHD filter.

Fast communication: Gaussian mixture importance sampling function for unscented SMC-PHD filter

The unscented sequential Monte Carlo probability hypothesis density (USMC-PHD) filter has been proposed to improve the accuracy performance of the bootstrap SMC-PHD filter in cluttered environments. However, the USMC-PHD filter suffers from heavy computational complexity because the unscented information filter is assigned for every particle to approximate an importance sampling function. In this paper, we propose a Gaussian mixture form of the importance sampling function for the SMC-PHD filter to considerably reduce the computational complexity without performance degradation. Simulation results support that the proposed importance sampling function is effective in computational aspects compared with variants of SMC-PHD filters and competitive to the USMC-PHD filter in accuracy.

Classification of road surface status using a 94 GHz dual-channel polarimetric radiometer

In this article, we classify road surface statuses using a Bayesian classification method. This article uses principal component analysis (PCA) that combines a 94 GHz dual-channel polarimetric radiometer. The radiometer is used to investigate the behaviour of the brightness temperature (BT) of different road surface statuses in an open-air laboratory. The aim of this investigation is to characterize four different road surface classes (dry, wet, snowy and icy). Here, the BT (radiothermal emission) characteristics are measured at horizontal and vertical polarizations. For a given database of weather information (including BT, road surface temperature, wind speed, etc.), a PCA subspace is constructed, and the score vectors are classified by solving the Bayesian classification method. As a result, the road surface statuses were found to be well classified by the proposed method in real time.

Dynamic Point Clustering with Line Constraints for Moving Object Detection in DAS

In this letter, we propose a robust dynamic point clustering method for detecting moving objects in stereo image sequences, which is essential for collision detection in driver assistance system. If multiple objects with similar motions are located in close proximity, dynamic points from different moving objects may be clustered together when using the position and velocity as clustering criteria. To solve this problem, we apply a geometric constraint between dynamic points using line segments. Based on this constraint, we propose a variable K-nearest neighbor clustering method and three cost functions that are defined between line segments and points. The proposed method is verified experimentally in terms of its accuracy, and comparisons are also made with conventional methods that only utilize the positions and velocities of dynamic points.

Distributed information fusion filter with intermittent observations

We present a robust distributed fusion algorithm with intermittent observations via an interacting multiple model (IMM) approach and sliding window strategy that can be applied to a large-scale sensor network. The communication channel is modelled as a jump Markov system and a posterior probability distribution for communication channel characteristics is calculated and incorporated into the filter to allow distributed Kalman filtering to automatically handle the intermittent observation situations. To implement distributed Kalman filtering, a Kalman-Consensus filter (KCF) is then used to obtain the average consensus based on the estimates of distributed sensors over a large-scale sensor network. From a target-tracking example for a large-scale sensor network with intermittent observations, the advantages of proposed algorithms are subsequently verified.