Adaptive Multi-cue 3D Tracking of Arbitrary Objects

García, Germán Martín; Klein, Dominik A.; Stückler, Jörg; Frintrop, Simone; Cremers, Armin B.

doi:10.1007/978-3-642-32717-9_36

Cited by 22 publications

(18 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…html and the ping pong ball video used in various literatures [5] [25]. Tracking object with occlusion is performed by video from trictrac (http://www.multitel.be/trictrac/) [26] as the seventh video.…”

Section: Test Videosmentioning

confidence: 99%

Particle Filter-Based Object Tracking Using Joint Features of Color and Local Binary Pattern Histogram Fourier

Wiharta

2016

kursor

View full text Add to dashboard Cite

show abstract

Section: Test Videosmentioning

confidence: 99%

Particle Filter-Based Object Tracking Using Joint Features of Color and Local Binary Pattern Histogram Fourier

Wiharta

2016

kursor

View full text Add to dashboard Cite

show abstract

“…With the advancement of sensor devices in imaging technologies and new algorithms in computer vision applications, different sensory type representations of the scene can be provided such as depth or disparity images, 3D point clouds, thermal images, and etc [12,[20][21][22][23]. For instance, Talha and Stolkin [20] proposed an adaptive system that utilize particle filter based subject tracking by fusing thermal and visible spectra camera.…”

Section: Background On Multi-sensor Approaches For Detection and Tracmentioning

confidence: 99%

“…Therefore, applications have been developed for detection and tracking by using color and depth data integration [21][22][23]. For example, Garcia et al [21] proposed particle filter model by representing the particle states with 3D world coordinates and particle features with depth gradients and polar representation of color averages from HSV color space Cartesian definition [21].…”

Section: Background On Multi-sensor Approaches For Detection and Tracmentioning

confidence: 99%

Top-down Spatial Attention for Visual Search: Novelty Detection-Tracking Using Spatial Memory with a Mobile Robot

İmamoğlu

Dorronzoro

Sekine

et al. 2014

AIVP

View full text Add to dashboard Cite

Assistive robotics technologies have been growing impact on at-home monitoring services to support daily life. One of the main research fields is to develop an autonomous mobile robot with the tasks detection, tracking, observation and analysis of the subject of interest in the indoor environment. The main challenges in such daily monitoring application, thus in visual search, are that the robot should track the subject successfully in several severe varying conditions. Recent color and depth image based visual search methods can help to handle part of the problems, such as changing illumination, occlusion, and etc. but these methods generally use large amount of training data by checking the whole scene with high redundancy to find the region of interest. Therefore, inspired by the idea that spatial memory can reveal novelty regions for finding the attention points as in Human Visual System (HVS), we proposed a simple and novel algorithm that integrates Kinect and Lidar(Light Detection And Ranging) sensor data to detect and track novelties using the environment map of the robot as a topdown approach without the necessity of large amount of training data. Then, novelty detection and tracking is achieved based on space based saliency map representing the novelty on the scene. Experimental results demonstrated that the proposed visual attention based scene analysis can handle various conditions stated and achieve high accuracy of novelty detection and tracking.

show abstract

“…The results from a few, recent works in RGB-D tracking have demonstrated that state-of-the-art RGB tracking algorithms can be outperformed by approaches that fuse colour and depth, for example [1,3,4,5].In this paper, we propose a real-time RGB-D tracker which we refer to as the Depth Scaling Kernalised Correlations Filters (DS-KCF). It is based on, and improves upon, the RGB Kernelised Correlation Filters tracker (KCF) from [2].…”

mentioning

confidence: 99%

mentioning

confidence: 99%

Real-time RGB-D Tracking with Depth Scaling Kernelised Correlation Filters and Occlusion Handling

Camplani¹,

Hannuna²,

Mirmehdi³

et al. 2015

Procedings of the British Machine Vision Conference 2015

View full text Add to dashboard Cite

The recent surge in popularity of real-time RGB-D sensors has encouraged research into combining colour and depth data for tracking. The results from a few, recent works in RGB-D tracking have demonstrated that state-of-the-art RGB tracking algorithms can be outperformed by approaches that fuse colour and depth, for example [1,3,4,5].In this paper, we propose a real-time RGB-D tracker which we refer to as the Depth Scaling Kernalised Correlations Filters (DS-KCF). It is based on, and improves upon, the RGB Kernelised Correlation Filters tracker (KCF) from [2]. KCF is based on the use of the 'kernel trick' to extend correlation filters for very fast RGB tracking. The KCF tracker has important characteristics, in particular its ability to combine high accuracy and processing speed as demonstrated in [2,6]. It is based on a simple processing chain that comprises training, detection, retraining and model update obtained by linear interpolation. The key to KCF is that it exploits the properties of circulant matrices to achieve efficient learning by implicitly encoding convolution and by allowing to operate in the Fourier domain using mainly element wise operations.The proposed DS-KCF tracker 1 extends the RGB KCF tracker in three ways: (i) we employ an the efficient combination of colour and depth features (ii) we propose an efficient a novel management of scale changes and (iii) occlusions handling. The improvements we implement provide higher rates of accuracy while still operating at better than real-time frame rates (35fps on average ). In particular, depth data in the target region is segmented with a fast K-means approach to extract relevant features for the target's depth distribution. Modelled as a Gaussian distribution, this data allows to identify scale changes and efficiently model them in the Fourier domain. The advantage of the proposed approach is that only a single target model is kept and updated. Furthermore, region depth distribution enables the detection of possible occlusions identified as sudden changes in the target region's depth histogram, and recovering lost tracks by searching for the unoccluded object in specifically identified key areas. During an occlusion, the model is not updated and the occluding object is tracked to guide the target's search space.

show abstract

Adaptive Multi-cue 3D Tracking of Arbitrary Objects

Cited by 22 publications

References 19 publications

Particle Filter-Based Object Tracking Using Joint Features of Color and Local Binary Pattern Histogram Fourier

Particle Filter-Based Object Tracking Using Joint Features of Color and Local Binary Pattern Histogram Fourier

Top-down Spatial Attention for Visual Search: Novelty Detection-Tracking Using Spatial Memory with a Mobile Robot

Real-time RGB-D Tracking with Depth Scaling Kernelised Correlation Filters and Occlusion Handling

Contact Info

Product

Resources

About