Skip to Main content Skip to Navigation
Conference papers

Small moving target MOT tracking with GM-PHD filter and attention-based CNN

Abstract : We present a multi-object tracking (MOT) approach to track small moving targets in satellite images. Our objects of interest span few pixels, do not present a defined texture, and are easily lost in cluttered environments. We propose a patchbased convolutional neural network (CNN) that focuses on specific regions to detect and discriminate nearby small objects. We use the object motion information to drive the patch selection and detect objects using a region-based CNN. In addition, we present a direct MOT data-association approach by using an improved Gaussian mixture-probability hypothesis density (GM-PHD) filter. The GM-PHD filter offers an efficient yet robust MOT formulation that takes into account clutter, misdetection, and target appearance and disappearance. We are able to detect and track blob-like moving objects and demonstrate an improvement over competing state-of-the-art tracking approaches.
Complete list of metadata

https://hal.inria.fr/hal-03351017
Contributor : Jules Mabon Connect in order to contact the contributor
Submitted on : Wednesday, September 22, 2021 - 4:41:17 PM
Last modification on : Monday, September 27, 2021 - 10:11:44 AM

File

MLSP_2021_hal.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-03351017, version 1

Citation

Camilo Aguilar, Mathias Ortner, Josiane Zerubia. Small moving target MOT tracking with GM-PHD filter and attention-based CNN. IEEE international workshop on machine learning for signal processing (MLSP 2021), Oct 2021, Gold Coast / Virtual, Australia. ⟨hal-03351017⟩

Share

Metrics

Record views

56

Files downloads

199