ML Anthology

Saliency-Based Detection for Maritime Object Tracking

Tom Cane, James M. Ferryman
CVPRW 2016 pp. 1257-1264
doi:10.1109/CVPRW.2016.159 /cvprw/2016/cane2016cvprw-saliencybased/

Abstract

This paper presents a new method for object detection and tracking based on visual saliency as a way of mitigating against challenges present in maritime environments. Object detection is based on adaptive hysteresis thresholding of a saliency map generated with a modified version of the Boolean Map Saliency (BMS) approach. We show that the modification reduces false positives by suppressing detection of wakes and surface glint. Tracking is performed by matching detections frame to frame and smoothing trajectories with a Kalman filter. The proposed approach is evaluated on the PETS 2016 challenge dataset on detecting and tracking boats around a vessel at sea.

CVPRW Semantic Scholar

Cite

Text

Cane and Ferryman. "Saliency-Based Detection for Maritime Object Tracking." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2016. doi:10.1109/CVPRW.2016.159

Markdown

[Cane and Ferryman. "Saliency-Based Detection for Maritime Object Tracking." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2016.](https://mlanthology.org/cvprw/2016/cane2016cvprw-saliencybased/) doi:10.1109/CVPRW.2016.159

BibTeX

@inproceedings{cane2016cvprw-saliencybased,
  title     = {{Saliency-Based Detection for Maritime Object Tracking}},
  author    = {Cane, Tom and Ferryman, James M.},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops},
  year      = {2016},
  pages     = {1257-1264},
  doi       = {10.1109/CVPRW.2016.159},
  url       = {https://mlanthology.org/cvprw/2016/cane2016cvprw-saliencybased/}
}