A survey on leveraging deep neural networks for object tracking

Krebs, Sebastian; Duraisamy, Bharanidhar; Flohr, Fabian

doi:10.1109/itsc.2017.8317904

Cited by 36 publications

(17 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Various studies published in recent years prove that the family of convolutional neural network topologies (CNN) outperforms classical image processing methods in tasks of object detection and classification benchmarked on various datasets [14,15]. Following this fact, we propose a detection and positioning system, that uses CNN to transform the original RGB image of the monitored area into a specific schematic image.…”

Section: Detection and Positioning Systemmentioning

confidence: 99%

Efficient 2D Detection and Positioning of Complex Objects for Robotic Manipulation Using Fully Convolutional Neural Network

Štursa¹,

Honc²,

Doležel³

2021

Adv. sci. technol. eng. syst. j.

View full text Add to dashboard Cite

Programming industrial robots in a real-life environment is a significant task necessary to be dealt with in modern facilities. The "pick up and place" task is undeniably one of the regular robot programming problems which needs to be solved. At the beginning of the "pick and place" task, the position determination and exact detection of the objects for picking must be performed. In this paper, an advanced approach to the detection and positioning of various objects is introduced. The approach is based on two consecutive steps. Firstly, the captured scene, containing attentive objects, is transformed using a segmentation neural network. The output of the segmentation process is a schematic image in which the types and positions of objects are represented by gradient circles of various colors. Secondly, these particular circle positions are determined by finding the local maxima in the schematic image. The proposed approach is tested on a complex detection and positioning problem by evaluation of total accuracy.

show abstract

Section: Detection and Positioning Systemmentioning

confidence: 99%

Efficient 2D Detection and Positioning of Complex Objects for Robotic Manipulation Using Fully Convolutional Neural Network

Štursa¹,

Honc²,

Doležel³

2021

Adv. sci. technol. eng. syst. j.

View full text Add to dashboard Cite

show abstract

“…Deep predictive motion tracking using RNNs based on video sequences has also been widely studied in robotics and computer vision, e.g. [40]- [42]. A review of these studies is beyond the scope of this paper, but we briefly review some representative methods and studies.…”

Section: B Related Workmentioning

confidence: 99%

Deep Predictive Motion Tracking in Magnetic Resonance Imaging: Application to Fetal Imaging

Singh

Salehi²,

Gholipour

2020

IEEE Trans. Med. Imaging

View full text Add to dashboard Cite

Fetal magnetic resonance imaging (MRI) is challenged by uncontrollable, large, and irregular fetal movements. It is, therefore, performed through visual monitoring of fetal motion and repeated acquisitions to ensure diagnostic-quality images are acquired. Nevertheless, visual monitoring of fetal motion based on displayed slices, and navigation at the level of stacks-of-slices is inefficient. The current process is highly operator-dependent, increases scanner usage and cost, and significantly increases the length of fetal MRI scans which makes them hard to tolerate for pregnant women. To help build automatic MRI motion tracking and navigation systems to overcome the limitations of the current process and improve fetal imaging, we have developed a new real-time image-based motion tracking method based on deep learning that learns to predict fetal motion directly from acquired images. Our method is based on a recurrent neural network, composed of spatial and temporal encoder-decoders, that infers motion parameters from anatomical features extracted from sequences of acquired slices. We compared our trained network on held-out test sets (including data with different characteristics, e.g. different fetuses scanned at different ages, and motion trajectories recorded from volunteer subjects) with networks designed for estimation as well as methods adopted to make predictions. The results show that our method outperformed alternative techniques, and achieved real-time performance with average errors of 3.5 and 8 degrees for the estimation and prediction tasks, respectively. Our real-time deep predictive motion tracking technique can be used to assess fetal movements, to guide slice acquisitions, and to build navigation systems for fetal MRI.

show abstract

“…Existing visual tracking methods [33], [34], which use lowlevel features, do not directly solve the problem of unforeseen visual disturbance for micromanipulation. Recently, advances in supervised learning approaches demonstrate an effective solution to combat visual tracking failure [35]- [37]. However, visual servo applications require low computational cost less computationally intensive tracking of low-level features.…”

Section: Related Workmentioning

confidence: 99%

Confidence-Based Hybrid Tracking to Overcome Visual Tracking Failures in Calibration-Less Vision-Guided Micromanipulation

Yang

Paranawithana

Tan

2020

IEEE Trans. Automat. Sci. Eng.

View full text Add to dashboard Cite

This article proposes a confidence-based approach for combining two visual tracking techniques to minimize the influence of unforeseen visual tracking failures to achieve uninterrupted vision-based control. Despite research efforts in vision-guided micromanipulation, existing systems are not designed to overcome visual tracking failures, such as inconsistent illumination condition, regional occlusion, unknown structures, and nonhomogenous background scene. There remains a gap in expanding current procedures beyond the laboratory environment for practical deployment of vision-guided micromanipulation system. A hybrid tracking method, which combines motion-cue feature detection and score-based template matching, is incorporated in an uncalibrated vision-guided workflow capable of self-initializing and recovery during the micromanipulation. Weighted average, based on the respective confidence indices of the motion-cue feature localization and template-based trackers, is inferred from the statistical accuracy of feature locations and the similarity score-based template matches. Results suggest improvement of the tracking performance using hybrid tracking under the conditions. The mean errors of hybrid tracking are maintained at subpixel level under adverse experimental conditions while the original template matching approach has mean errors of 1.53, 1.73, and 2.08 pixels. The method is also demonstrated to be robust in the nonhomogeneous scene with an array of plant cells. By proposing a self-contained fusion method that overcomes unforeseen visual tracking failures using pure vision approach, we demonstrated the robustness in our developed low-cost micromanipulation platform.

show abstract

A survey on leveraging deep neural networks for object tracking

Cited by 36 publications

References 34 publications

Efficient 2D Detection and Positioning of Complex Objects for Robotic Manipulation Using Fully Convolutional Neural Network

Efficient 2D Detection and Positioning of Complex Objects for Robotic Manipulation Using Fully Convolutional Neural Network

Deep Predictive Motion Tracking in Magnetic Resonance Imaging: Application to Fetal Imaging

Confidence-Based Hybrid Tracking to Overcome Visual Tracking Failures in Calibration-Less Vision-Guided Micromanipulation

Contact Info

Product

Resources

About