Contrasting YOLOv5, transformer, and EfficientDet detectors for crop circle detection in desert

ML Mekhalfi, C Nicolò, Y Bazi… - … and Remote Sensing …, 2021 - ieeexplore.ieee.org
Ongoing discoveries of water reserves have fostered an increasing adoption of crop circles
in the desert in several countries. Automatically quantifying and surveying the layout of crop …

Instance enhancing loss: Deep identity-sensitive feature embedding for person search

W Shi, H Liu, F Meng, W Huang - 2018 25th IEEE International …, 2018 - ieeexplore.ieee.org
Person search, which is vital for intelligent surveillance, aims at detecting and re-identifying
pedestrians from whole monitoring images. However, due to the inaccurate pedestrian …

Enhanced feature fusion through irrelevant redundancy elimination in intra-class and extra-class discriminative correlation analysis

Z Wu, K Mao, GW Ng - Neurocomputing, 2019 - Elsevier
Feature fusion aims to provide enhancements of data authenticity in both traditional and
deep learning pattern analysis. Canonical correlation analysis (CCA) based feature fusion is …

Re-ranking image-text matching by adaptive metric fusion

K Niu, Y Huang, L Wang - Pattern Recognition, 2020 - Elsevier
Image-text matching has drawn much attention recently with the rapid growth of multi-modal
data. Many effective approaches have been proposed to solve this challenging problem, but …

Multi similarity metric fusion in graph-based semi-supervised learning

S Bahrami, A Bosaghzadeh, F Dornaika - Computation, 2019 - mdpi.com
In semi-supervised label propagation (LP), the data manifold is approximated by a graph,
which is considered as a similarity metric. Graph estimation is a crucial task, as it affects the …

Multi-level cross-view consistent feature learning for person re-identification

Y Liu, Y Zhang, B Bhanu, S Coleman, D Kerr - Neurocomputing, 2021 - Elsevier
Person re-identification plays an important role in searching for a specific person in a
camera network with non-overlapping cameras. The most critical problem for re …

Detecting crop circles in google earth images with mask R-CNN and YOLOv3

ML Mekhalfi, C Nicolò, Y Bazi, MM Al Rahhal… - Applied Sciences, 2021 - mdpi.com
Automatic detection and counting of crop circles in the desert can be of great use for large-
scale farming as it enables easy and timely management of the farming land. However, so …

Appearance model update based on online learning and soft‐biometrics traits for people re‐identification in multi‐camera environments

D Moctezuma, ES Tellez… - IET Image …, 2019 - Wiley Online Library
Intelligent surveillance systems in multi‐camera environments pose a hard‐open problem
for computer vision. The way the people look changes inside and also among cameras, so …

Robust Person Re-identification through fusion of discriminant and deep Features

A Merabet, A Ouafi, F Moussi… - 2024 8th International …, 2024 - ieeexplore.ieee.org
Person re-identification is a crucial task within the realm of computer vision and surveillance,
aiming to identify and track individuals across various camera views or frames. It is …

Adaptive re-ranking of deep feature for person re-identification

Y Liu, L Shang, A Song - arXiv preprint arXiv:1811.08561, 2018 - arxiv.org
Typical person re-identification (re-ID) methods train a deep CNN to extract deep features
and combine them with a distance metric for the final evaluation. In this work, we focus on …