Authors:
Joaquin Palma-Ugarte
1
;
Laura Estacio-Cerquin
2
;
3
;
Victor Flores-Benites
4
and
Rensso Mora-Colque
1
Affiliations:
1
Department of Computer Science, Universidad Católica San Pablo, Arequipa, Peru
;
2
Department of Radiology, The Netherlands Cancer Institute - Antoni van Leeuwenhoek Hospital, Amsterdam, The Netherlands
;
3
GROW School for Oncology and Developmental Biology, Maastricht University, Maastricht, The Netherlands
;
4
Universidad de Ingeniería y Tecnología – UTEC, Lima, Peru
Keyword(s):
Detection, Classification, Moving Objects, Gaussian Mixture, Lightweight Model.
Abstract:
Moving object detection and classification are fundamental tasks in computer vision. However, current solutions detect all objects, and then another algorithm is used to determine which objects are in motion. Furthermore, diverse solutions employ complex networks that require a lot of computational resources, unlike
lightweight solutions that could lead to widespread use. We introduce TRG-Net, a unified model that can be
executed on computationally limited devices to detect and classify just moving objects. This proposal is based
on the Faster R-CNN architecture, MobileNetV3 as a feature extractor, and a Gaussian mixture model for a
fast search of regions of interest based on motion. TRG-Net reduces the inference time by unifying moving
object detection and image classification tasks, and by limiting the regions of interest to the number of moving objects. Experiments over surveillance videos and the Kitti dataset for 2D object detection show that our
approach improves the infe
rence time of Faster R-CNN (0.221 to 0.138s) using fewer parameters (18.91 M to
18.30 M) while maintaining average precision (AP=0.423). Therefore, TRG-Net achieves a balance between
precision and speed, and could be applied in various real-world scenarios.
(More)