In recent years, object tracking based on Siamese network has attracted the attention by taking advantage of both speed and accuracy. However, when similar object interference, severe occlusion and other factors cause...
详细信息
In recent years, object tracking based on Siamese network has attracted the attention by taking advantage of both speed and accuracy. However, when similar object interference, severe occlusion and other factors cause temporary trackingfailure, a restricted search window makes Siamese network difficult to retrieve the object again, and results in unrecoverable trackingfailures. In this paper, a general and efficient two-way verification tracking failure detection method using parallel correlation filtering and Siamese network is proposed, which can detect the trackingfailure and retrieve the object again. Firstly, we construct parallel Siamese network and correlation filter tracking network, and get tracking results respectively. Secondly, we make a preliminary judgment on the reliability of the tracking results based on the overlap ratio of the tracking results. Finally, based on two-way verification, which tracker failed to track is finally determined, and the search window of Siamese network is optimized to retrieve the object again. We comparisons with state-of-the art trackers on benchmark datasets: OTB100, VOT2016, VOT2018, VOT2019 and NFS. The results show that the method we proposed can detect the trackingfailure and retrieve the object again, thus improving the accuracy of object tracking.
Despite the benefits introduced by robotic systems in abdominal Minimally Invasive Surgery (MIS), major complications can still affect the outcome of the procedure, such as intra-operative bleeding. One of the causes ...
详细信息
Despite the benefits introduced by robotic systems in abdominal Minimally Invasive Surgery (MIS), major complications can still affect the outcome of the procedure, such as intra-operative bleeding. One of the causes is attributed to accidental damages to arteries or veins by the surgical tools, and some of the possible risk factors are related to the lack of sub-surface visibilty. Assistive tools guiding the surgical gestures to prevent these kind of injuries would represent a relevant step towards safer clinical procedures. However, it is still challenging to develop computer vision systems able to fulfill the main requirements: (i) long term robustness, (ii) adaptation to environment/object variation and (iii) real time processing. The purpose of this paper is to develop computer vision algorithms to robustly track soft tissue areas (Safety Area, SA), defined intra-operatively by the surgeon based on the real-time endoscopic images, or registered from a pre-operative surgical plan. We propose a framework to combine an optical flow algorithm with a tracking-by-detection approach in order to be robust against failures caused by: (i) partial occlusion, (ii) total occlusion, (iii) SA out of the field of view, (iv) deformation, (v) illumination changes, (vi) abrupt camera motion, (vii), blur and (viii) smoke. A Bayesian inference-based approach is used to detect the failure of the tracker, based on online context information. A Model Update Strategy (MUpS) is also proposed to improve the SA re-detection after failures, taking into account the changes of appearance of the SA model due to contact with instruments or image noise. The performance of the algorithm was assessed on two datasets, representing ex-vivo organs and in-vivo surgical scenarios. Results show that the proposed framework, enhanced with MUpS, is capable of maintain high tracking performance for extended periods of time (similar or equal to 4 min - containing the aforementioned events) with high precisi
In this paper, we present a tracking failure detection method by imitating human visual system. By adopting log-polar transformation, we could simulate properties of retina image, such as rotation and scaling invarian...
详细信息
ISBN:
(纸本)9781457713033
In this paper, we present a tracking failure detection method by imitating human visual system. By adopting log-polar transformation, we could simulate properties of retina image, such as rotation and scaling invariance and foveal predominance. The rotation and scaling invariance helps to reduce false alarms caused by pose changes and intensify translational changes. Foveal predominant property helps to detect the tracking failing moment by amplifying the resolution around focus (tracking box center) and blurring the peripheries. Each ganglion cell corresponds to a pixel of log-polar image, and its adaptation is modeled as Gaussian mixture model. Its validity is shown through various experiments.
暂无评论