Automatic Calibration of Stationary Surveillance Cameras in the Wild

Brouwers, Guido M. Y. E.; Zwemer, Matthijs H.; Wijnhoven, Rob G. J.

doi:10.1007/978-3-319-48881-3_52

Cited by 11 publications

(8 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…There are two video sequences, Outdoorand Indoor, from the VPTZ benchmark [32] for virtual PTZ camera simulation and a sequence, Terrace, from the EPFL benchmark [33] for multi-camera pedestrian detection and tracking. These three sequences have also been adopted in the work [16] for experimental comparison. Besides, we use two video sequences from the MOTChallenge 3D benchmark [34], PETS09-S2L1 and AVG-TownCentre.…”

Section: Resultsmentioning

confidence: 99%

“…Recently, Huang et al [15] develop a novel scheme that detects the image points of toes on the ground plane, which can directly infer the two vanishing points on L ∞ . The work [16] proposes preand post-processing stages to improve the estimation of V ∞ and L ∞ . Führ and Jung [17] adopt a nonlinear cost function aiming to mostly align the orientation of the reprojected poles.…”

Section: Related Work a Self-calibration From Human Trackingmentioning

confidence: 99%

“…To estimate V ∞ and L ∞ for camera calibration, the first step is to model each human instance as a pole perpendicular to the ground plane, which is equivalent to the 3D localization of head and foot points of the segmented human body. Most previous methods [8]- [16] assume they have accurate human tracking and segmentation data as input. For more practical usage, instead, we combine the state-of-the-art multi-target tracking and segmentation to support head/foot localization.…”

Section: A Tracking and Head/foot Localizationmentioning

confidence: 99%

“…• A recent method by Brouwers et al [16], which adds a pre-processing step to filter away detection outliers and a post-processing step for tilt angle optimization based on human height distribution…”

Section: A Comparison Of Camera Self-calibrationmentioning

confidence: 99%

See 3 more Smart Citations

ESTHER: Joint Camera Self-Calibration and Automatic Radial Distortion Correction From Tracking of Walking Humans

et al. 2019

View full text Add to dashboard Cite

Camera calibration and radial distortion correction are the crucial prerequisites for many applications in image big data and computer vision. Many existing works rely on the Manhattan world assumption to estimate the camera parameters automatically; however, they may perform poorly when there was lack of man-made structure in the scene. As walking humans are the common objects in video surveillance, they have also been used for camera self-calibration, but the main challenges include the noise reduction for the estimation of vanishing points, the relaxation of assumptions on unknown camera parameters, and the radial distortion correction. In this paper, we present a novel framework for camera self-calibration and automatic radial distortion correction. Our approach starts with the reliable human body segmentation that is facilitated by robust object tracking. Mean shift clustering and Laplace linear regression are, respectively, introduced in the estimation of the vertical vanishing point and the horizon line. The estimation of distribution algorithm, an evolutionary optimization scheme, is then utilized to optimize the camera parameters and the distortion coefficients, in which all the unknowns in camera projection can be fine-tuned simultaneously. Experiments on the three public benchmarks and our own captured dataset demonstrate the robustness of the proposed method. The superiority of this algorithm is also verified by the capability of reliably converting 2D object tracking into 3D space.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Related Work a Self-calibration From Human Trackingmentioning

confidence: 99%

Section: A Tracking and Head/foot Localizationmentioning

confidence: 99%

Section: A Comparison Of Camera Self-calibrationmentioning

confidence: 99%

See 2 more Smart Citations

ESTHER: Joint Camera Self-Calibration and Automatic Radial Distortion Correction From Tracking of Walking Humans

et al. 2019

View full text Add to dashboard Cite

show abstract

“…To aid for integration in a VTS, the locations are converted to GPS coordinates, requiring the camera to be calibrated. This camera calibration is performed based on the horizon line and the vertical vanishing point (Brouwers et al, 2016). In our application, we have defined the horizon line and vertical vanishing point by manually annotating several parallel lines in the camera image.…”

Section: Gps Location By Calibrationmentioning

confidence: 99%

Ship Detection in Harbour Surveillance based on Large-Scale Data and CNNs

Zwemer

Wijnhoven

With

2018

Proceedings of the 13th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Application

Self Cite

View full text Add to dashboard Cite

This paper aims at developing a real-time vessel detection and tracking system using surveillance cameras in harbours with the purpose to improve the current Vessel Tracking Systems (VTS) performance. To this end, we introduce a novel maritime dataset, containing 70,513 ships in 48,966 images, covering 10 camera viewpoints indicating real-life ship traffic situations. For detection, a Convolutional Neural Network (CNN) detector is trained, based on the Single Shot Detector (SSD) from literature. This detector is modified and enhanced to support the detection of extreme variations of ship sizes and aspect ratios. The modified SSD detector offers a high detection performance, which is based on explicitly exploiting the aspect-ratio characteristics of the dataset. The performance of the original SSD detector trained on generic object detection datasets (including ships) is significantly lower, showing the added value of a novel surveillance dataset for ships. Due to the robust performance of over 90% detection, the system is able to accurately detect all types of vessels. Hence, the system is considered a suitable complement to conventional radar detection, leading to a better operational picture for the harbour authorities. 1 APPS Project page: https://itea3.org/project/apps.html Zwemer, M., Wijnhoven, R. and With, P. Ship Detection in Harbour Surveillance based on Large-Scale Data and CNNs.

show abstract