Mitchell Rogers

Dr. Mitchell Rogers

orcid

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
17 August 2023 in Journal of Food Measurement and Characterization
Verified
Journal Article
Open access
PDF file
MRMitchell Rogers
Mitchell Rogers
JBJacques Blanc-Talon
Jacques Blanc-Talon
MUMartin Urschler
Martin Urschler
PDPatrice Delmas
Patrice Delmas
Over the past two decades, hyperspectral imaging has become popular for non-destructive assessment of food quality, safety, and crop monitoring. Imaging delivers spatial information to complement the spectral information provided by spectroscopy. The key challenge with hyperspectral image data is the high dimensionality. Each image captures hundreds of wavelength bands. Reducing the number of wavelengths to an optimal subset is essential for speed and robustness due to the high multicollinearity between bands. However, there is yet to be a consensus on the best methods to find optimal subsets of wavelengths to predict attributes of samples. A systematic review procedure was developed and applied to review published research on hyperspectral imaging and wavelength selection. The review population included studies from all disciplines retrieved from the Scopus database that provided empirical results from hyperspectral images and applied wavelength selection. We found that 799 studies satisfied the defined inclusion criteria and investigated trends in their study design, wavelength selection, and machine learning techniques. For further analysis, we considered a subset of 71 studies published in English that incorporated spatial/texture features to understand how previous works combined spatial features with wavelength selection. This review ranks the wavelength selection techniques from each study to generate a table of the comparative performance of each selection method. Based on these findings, we suggest that future studies include spatial feature extraction methods to improve the predictive performance and compare them to a broader range of wavelength selection techniques, especially when proposing novel methods.

6 February 2026 in International Journal of Computer Vision
Verified
Journal Article
Open access
PDF file
MRMitchell Rogers
Mitchell Rogers
KKKobe Knowles
Kobe Knowles
GGGaël Gendron
Gaël Gendron
SHShahrokh Heidari
Shahrokh Heidari
IDIsla C Duporge
Isla C Duporge
PDPatrice Delmas
Patrice Delmas
Recent advances in deep learning have greatly enhanced the accuracy and scalability of animal re-identification by automating the extraction of subtle distinguishing features from images and videos. This enables large-scale, non-invasive monitoring of animal populations. This article proposes a segmentation pipeline and a re-identification model to identify animals without ground-truth IDs. The segmentation pipeline isolates animals from the background using bounding boxes and leverages the DINOv2 and Segment Anything Model 2 (SAM2) foundation models. For re-identification, Recurrence over Video Frames (RoVF) is introduced, a novel approach that employs a recurrent component based on the Perceiver transformer atop a DINOv2 image model, iteratively refining embeddings from video frames. The proposed methods are evaluated on video datasets of meerkats and polar bears (PolarBearVidID). The proposed segmentation model achieved high accuracy (94.36% and 97.26%) and IoU (73.14% and 92.77%) for meerkats and polar bears, respectively. RoVF outperformed frame- and video-based re-identification baselines, achieving a top-1 accuracy of 46.5% and 55% on masked test sets for meerkats and polar bears, respectively, as well as higher top-3 accuracy. These results highlight the potential of the proposed approach to reduce annotation burdens in future individual-based ecological studies. The code is available at https://github.com/Strong-AI-Lab/RoVF-Meerkat-Reidentification .

14 November 2023
Verified
Book Chapter
Closed access
PDF file
MRMitchell Rogers
Mitchell Rogers
IDIgor Debski
Igor Debski
JFJohannes Fischer
Johannes Fischer
PMPeter McComb
Peter McComb
PFPeter Frost
Peter Frost
PDPatrice Delmas
Patrice Delmas

16 May 2025 in arXiv
Verified
Preprint
Open access
PDF file
MRMitchell Rogers
Mitchell Rogers
TTTheo Thompson
Theo Thompson
IDIsla Duporge
Isla Duporge
JFJohannes Fischer
Johannes Fischer
KPKlemens Pütz
Klemens Pütz
MZMengjie Zhang
Mengjie Zhang
Recent advancements in deep learning and aerial imaging have transformed wildlife monitoring, enabling researchers to survey wildlife populations at unprecedented scales. Unmanned Aerial Vehicles (UAVs) provide a cost-effective means of capturing high-resolution imagery, particularly for monitoring densely populated seabird colonies. In this study, we assess the performance of a general-purpose avian detection model, BirdDetector, in estimating the breeding population of Salvin's albatross (Thalassarche salvini) on the Bounty Islands, New Zealand. Using drone-derived imagery, we evaluate the model's effectiveness in both zero-shot and fine-tuned settings, incorporating enhanced inference techniques and stronger augmentation methods. Our findings indicate that while applying the model in a zero-shot setting offers a strong baseline, fine-tuning with annotations from the target domain and stronger image augmentation leads to marked improvements in detection accuracy. These results highlight the potential of leveraging pre-trained deep-learning models for species-specific monitoring in remote and challenging environments.

14 November 2023
Verified
Book Chapter
Closed access
PDF file
MOMartin Ooi
Martin Ooi
DVDavid Arturo Soriano Valdez
David Arturo Soriano Valdez
MRMitchell Rogers
Mitchell Rogers
RARachel Ababou
Rachel Ababou
KZKaiqi Zhao
Kaiqi Zhao
PDPatrice Delmas
Patrice Delmas

6 March 2026 in Information
Verified
Journal Article
Open access
PDF file
NDNipuna Lakshitha Saputhanthrige Don
Nipuna Lakshitha Saputhanthrige Don
MRMitchell Rogers
Mitchell Rogers
JZJunhong Zhao
Junhong Zhao
Bing XueBing Xue
Bing Xue
MZMengjie Zhang
Mengjie Zhang
Computer vision and machine learning have accelerated the automation of animal re-identification pipelines used in conservation programs worldwide. For species with distinctive markings, such as the spot patterns of giraffes, these automated methods are crucial for research and population monitoring purposes. However, many tools are designed for experts, and their implementation requires substantial technical expertise. Research teams often use specialist software and workflows that are not accessible to the general public. In a zoo setting, visitors lack a simple way to identify an individual animal, and unique features are easily missed by untrained visitors. This study presents a three-part solution: a web interface for zoo visitors to upload photos, a deep learning model for giraffe torso detection, and a fast re-identification method for matching observations to a gallery of known individuals using server-side processing. We compare several re-identification methods (RootSIFT, MiewID, and MegaDescriptor) using a consistent evaluation protocol and report both identification performance and system latency for this closed-set zoo setting. Taken together, this study presents a visitor-facing web system that integrates existing re-identification models into a modular, real-time pipeline for zoo deployment, lowering the barrier to visitor participation and making state-of-the-art re-identification methods more accessible to the general public.