Transformer-based Models for Enhanced Amur Tiger Re-Identification

Book chapter


Bai, Xufeng, Islam, Tasmina and Bin Azhar, M A Hannan 2024. Transformer-based Models for Enhanced Amur Tiger Re-Identification. in: 2024 IEEE 22nd World Symposium on Applied Machine Intelligence and Informatics (SAMI) IEEE.
AuthorsBai, Xufeng, Islam, Tasmina and Bin Azhar, M A Hannan
Abstract

Rapid urban growth, with its profound impact on natural habitats, intensifies the global risk faced by many wildlife species, driving them closer to the brink of extinction due to factors like habitat destruction, illegal hunting, and the challenges posed by climate change. The urgency of this situation is highlighted by the current status of the Amur tigers, emphasising the need for continuous observation to ensure their survival. Within this context, re-identification (Re-ID) emerges as the method for recognising individual entities based on previously captured data. This study is dedicated to the re-identification of Amur tigers, employing the Amur Tiger Re-identification in the Wild (ATRW) dataset and placing a significant emphasis on assessing various deep learning architectures, particularly focusing on transformer-based models. Several neural network architectures, including Vision Transformer (ViT), Multiple Granularity Network (MGN), and Neighbor Transformer (NFormer), were explored. The results indicate that transformer-based methods hold substantial promise for further advancements in re-identification tasks. Notably, the ViT model achieved an impressive mAP score of 80.8, while the combination of ViT with MGN yielded an exceptional mAP of 83.4, surpassing the best benchmark method by an 9.3% in a single-camera scenario. Additionally, the NFormer architecture demonstrated comparable results, boasting a mAP score of 81.1.

KeywordsAmur tiger re-identification; Transformer architectures; Wildlife conservation; Multi-granularity network; Vision transformer; Neighbour transformer
Year2024
Book title2024 IEEE 22nd World Symposium on Applied Machine Intelligence and Informatics (SAMI)
PublisherIEEE
Output statusPublished
Publication dates
Print25 Jan 2024
Publication process dates
Deposited19 Feb 2024
Digital Object Identifier (DOI)https://doi.org/10.1109/sami60510.2024.10432893
Official URLhttps://ieeexplore.ieee.org/document/10432893
EventIEEE 22nd World Symposium on Applied Machine Intelligence and Informatics
Web address (URL) of conference proceedingshttps://ieeexplore.ieee.org/xpl/conhome/10432771/proceeding
Permalink -

https://repository.canterbury.ac.uk/item/971q8/transformer-based-models-for-enhanced-amur-tiger-re-identification

  • 45
    total views
  • 0
    total downloads
  • 1
    views this month
  • 0
    downloads this month

Export as

Related outputs

Unveiling pollution peaks: Comparing swarm intelligence with drone hill climber
Prior, O., Bin Azhar, M A Hannan, Sahota, V. and Turner, S. 2024. Unveiling pollution peaks: Comparing swarm intelligence with drone hill climber.
A qualitative review of educational robots for STEM: Technical features and impacts
Manna, Soumya Kanti, Azhar, M. A. Hannan Bin and Greace, Ann 2024. A qualitative review of educational robots for STEM: Technical features and impacts. in: Proceedings of the International Convention MIPRO IEEE.
Innovative assistive device to enhance wrist drop treatment in patients
Trainer, C., Manna, S. and Azhar, H. 2024. Innovative assistive device to enhance wrist drop treatment in patients. in: Costin, H-N., Magjarević, R. and Petroiu, G. G. (ed.) Advances in Digital Health and Medical Bioengineering: Proceedings of the 11th International Conference on E-Health and Bioengineering, EHB-2023, November 9–10, 2023, Bucharest, Romania – Volume 2: Health Technology Assessment, Biomedical Signal Processing, Medicine and Informatics Cham Springer. pp. 489-497
Tele-controlled upper arm exoskeleton for post-stroke recovery
Manna, S., Khan, A., Dilley, O. and Azhar, H. 2024. Tele-controlled upper arm exoskeleton for post-stroke recovery. in: Costin, H-N, Magjarević, R. and Petroiu, G. G. (ed.) Advances in Digital Health and Medical Bioengineering Cham Springer.
Metaverse application forensics: Unravelling the virtual truth
Azhar, H. and Rush-Gadsby, O. Metaverse application forensics: Unravelling the virtual truth. in: Cybersecurity Challenges in the Age of AI, Space Communications and Cyborgs Proceedings of the 15th International Conference on Global Security, Safety and Sustainability, London, October 2023 Cham Springer. pp. 399-414
Breaking barriers: A novel framework to evaluate usability of accessibility applications
Azhar, H., Islam, T. and Marczak, J. 2023. Breaking barriers: A novel framework to evaluate usability of accessibility applications. in: 36th International BCS Human-Computer Interaction Conference British Computer Society. pp. 23-33
An interactive web portal for customised telerehabilitation in neurological care
Hannan Bin Azhar, M A, Mészáros, Zoltán, Islam, Tasmina and Manna, Soumya K. 2023. An interactive web portal for customised telerehabilitation in neurological care. in: 2023 IEEE 22nd International Conference on Trust, Security and Privacy in Computing and Communications (TrustCom) IEEE. pp. 1814-1821
Trustworthy insights: A novel multi-tier explainable framework for ambient assisted living
Kasirajan, Merlin, Bin Azhar, M A Hannan and Turner, Scott 2023. Trustworthy insights: A novel multi-tier explainable framework for ambient assisted living. in: 2023 IEEE 22nd International Conference on Trust, Security and Privacy in Computing and Communications (TrustCom) IEEE. pp. 2554-2561
Assistive telehealth systems for neurorehabilitation
Azhar, H. 2023. Assistive telehealth systems for neurorehabilitation.
Optimal locations and computational frameworks of FSR and IMU sensors for measuring gait abnormalities
Manna, S., Azhar, H. and Greace, A. 2023. Optimal locations and computational frameworks of FSR and IMU sensors for measuring gait abnormalities. Heliyon. 9 (4), p. e15210. https://doi.org/10.1016/j.heliyon.2023.e15210
Spying on kids’ smart devices: Beware of security vulnerabilities!
Azhar, H., Smith, D. and Cain, A. 2023. Spying on kids’ smart devices: Beware of security vulnerabilities! in: Jahankhani, H. (ed.) Cybersecurity in the Age of Smart Societies Proceedings of the 14th International Conference on Global Security, Safety and Sustainability, London, September 2022 Springer. pp. 123-140
Cyber threats and exploits during the pandemic
Lo, J. and Azhar, H. Cyber threats and exploits during the pandemic. ASEAN Tech and Security, Singapore .
Z is for Zoombombing
Azhar, H. 2022. Z is for Zoombombing. Medium.
Progressive web app for real-time doctor-patient communication and searchable health conditions
Hannan Bin Azhar, M A and Mohan, Joseph Thomas 2022. Progressive web app for real-time doctor-patient communication and searchable health conditions. 2022 E-Health and Bioengineering Conference (EHB). https://doi.org/10.1109/EHB55594.2022.9991288
A smart and home-based telerehabilitation tool for patients with neuromuscular disorder
Manna, Soumya K., Hannan, M. A., Azhar, B., Smith, D. and Islam, T. 2022. A smart and home-based telerehabilitation tool for patients with neuromuscular disorder. IEEE. https://doi.org/10.1109/iecbes54088.2022.10079410
Forensic investigations of Google Meet and Microsoft Teams – two popular conferencing tools in the Pandemic
Azhar, H., Timms, J. and Tilley, B. 2022. Forensic investigations of Google Meet and Microsoft Teams – two popular conferencing tools in the Pandemic. in: Digital Forensics and Cyber Crime Springer Nature. pp. 20-34
Tele-tDCS: A Novel Tele-neuromodulation Framework using Internet of Medical Things
Herring, Samuel, Azhar, M. A. Hannan Bin and Sakel, Mohamed 2022. Tele-tDCS: A Novel Tele-neuromodulation Framework using Internet of Medical Things. in: Proceedings of the 15th International Joint Conference on Biomedical Engineering Systems and Technologies - BIODEVICES Setúbal, Portugal SCITEPRESS - Science and Technology Publications. pp. 84-93
Automatic identification of non-biting midges (Chironomidae) using object detection and deep learning techniques
Hollister, Jack, Vega, Rodrigo and Azhar, M. A. Hannan Bin 2022. Automatic identification of non-biting midges (Chironomidae) using object detection and deep learning techniques. in: Marsico, Maria D., Sanniti de Baja, Gabriella and Fred, Ana (ed.) Proceedings of the 11 International Conference on Pattern Recognition Applications and Methods SCITEPRESS - Science and Technology Publications.
A smart and secure IoMT tele-neurorehabilitation framework for post-stroke patients
Manna, S., Azhar, H. and Sakel, M. 2022. A smart and secure IoMT tele-neurorehabilitation framework for post-stroke patients. in: Bhaumik, S., Chattopadhyay, S., Chattopadhyay, T. and Bhattacharya, S. (ed.) Proceedings of International Conference on Industrial Instrumentation and Control ICI2C 2021 Singapore Springer. pp. 11-20
An inclusive student-led online class test during the pandemic
Manna, S. and Azhar, H. 2021. An inclusive student-led online class test during the pandemic . Assessment and Feedback Symposium 2021.
A forensic tool to acquire radio signals using software defined radio
Azhar, H. and Abadia, G. 2021. A forensic tool to acquire radio signals using software defined radio. in: Security and Privacy in Communication Networks : 17th EAI International Conference, SecureComm 2021, Virtual Event, September 6-9, 2021, Proceedings, Part I Springer.
Post-pandemic digital education: Investigating smart workspaces within the higher education sector
Azhar, M A Hannan Bin, Lepore, Emily Louise and Islam, T. 2021. Post-pandemic digital education: Investigating smart workspaces within the higher education sector. Proceedings of the BCS 34th British HCI Conference 2021. 34, pp. 284-288. https://doi.org/10.14236/ewic/hci2021.30
A study of user experiences and network analysis on anonymity and traceability of bitcoin transactions
Azhar, M.A.H.B and Whitehead, R.V. 2021. A study of user experiences and network analysis on anonymity and traceability of bitcoin transactions. EAI Endorsed Transactions on Security and Safety. https://doi.org/10.4108/eai.30-4-2021.169577
BCI controlled robotic arm as assistance to the rehabilitation of neurologically disabled patients
Azhar, H. 2021. BCI controlled robotic arm as assistance to the rehabilitation of neurologically disabled patients.
Forensic investigations of popular ephemeral messaging applications on Android and iOS platforms
Azhar, H., Cox, R. and Chamberlain, A. 2020. Forensic investigations of popular ephemeral messaging applications on Android and iOS platforms. International Journal on Advances in Security. 13 (1 & 2), pp. 41 - 53.
Comparisons of forensic tools to recover ephemeral data from iOS apps used for cyberbullying
Chamberlain, A. and Azhar, H. 2019. Comparisons of forensic tools to recover ephemeral data from iOS apps used for cyberbullying. in: CYBER 2019, The Fourth International Conference on Cyber-Technologies and Cyber-Systems IARIA. pp. 88-93
Recovery of forensic artefacts from a smart home IoT ecosystem
Azhar, H. and Bate, S. 2019. Recovery of forensic artefacts from a smart home IoT ecosystem. in: CYBER 2019, The Fourth International Conference on Cyber-Technologies and Cyber-Systems IARIA. pp. 94-99
BCI controlled robotic arm as assistance to the rehabilitation of neurologically disabled patients
Casey, A., Azhar, H., Grzes, M. and Sakel, M. 2019. BCI controlled robotic arm as assistance to the rehabilitation of neurologically disabled patients. Disability and Rehabilitation: Assistive Technology. 16 (5), pp. 525-537. https://doi.org/10.1080/17483107.2019.1683239
Effects of students’ preferences in use of lighting and temperature on productivity in a university setting
Azhar, H., Islam, T. and Alfieri, M. 2019. Effects of students’ preferences in use of lighting and temperature on productivity in a university setting. in: Zheng, P., Callaghan, V., Crawford, D., Kymalainen, T. and Reyes-Munoz, A. (ed.) EAI International Conference on Technology, Innovation, Entrepreneurship and Education Springer.
Use of wearable technology to measure emotional responses amongst tennis players
Azhar, H., Nelson, T. and Casey, A. 2019. Use of wearable technology to measure emotional responses amongst tennis players. in: Zheng, P., Callaghan, V., Crawford, D., Kymalainen, T. and Reyes-Munoz, A. (ed.) EAI International Conference on Technology, Innovation, Entrepreneurship and Education Springer.
Drone forensic analysis using open source tools
Azhar, H., Barton, T. and Islam, T. 2018. Drone forensic analysis using open source tools. Journal of Digital Forensics, Security and Law. 13 (1), pp. 7-30.
A cost-effective BCI assisted technology framework for neurorehabilitation
Azhar, H., Casey, A. and Sakel, M. 2018. A cost-effective BCI assisted technology framework for neurorehabilitation.
An investigation on forensic opportunities to recover evidential data from mobile phones and personal computers
Naughton, P. and Azhar, H. 2017. An investigation on forensic opportunities to recover evidential data from mobile phones and personal computers.
BCI controlled robotic arm as assistance to the rehabilitation of neurologically disabled patients
Azhar, H., Barton, T., Casey, A. and Sakel, M. 2017. BCI controlled robotic arm as assistance to the rehabilitation of neurologically disabled patients. Research and Knowledge Exchange Conference 2017.
Open source forensics for a multi-platform drone system
Barton, T. and Azhar, H. 2018. Open source forensics for a multi-platform drone system. in: Matousek, P. and Schmiedecker, M. (ed.) 9th EAI International Conference on Digital Forensics & Cyber Crime Springer. pp. 83-96
Evaluation of the MPS Predictive Policing Trial (redacted)
Bryant, R., Azhar, H., Blackburn, B. and Falade, M. 2015. Evaluation of the MPS Predictive Policing Trial (redacted).
Forensic analysis of popular UAV systems
Barton, T. and Azhar, H. 2017. Forensic analysis of popular UAV systems. Emerging Security Technologies (EST), 2017 Seventh International Conference on. https://doi.org/10.1109/EST.2017.8090405
A wearable brain-computer interface controlled robot
Azhar, H., Badicioiu, A. and Barton, T. 2016. A wearable brain-computer interface controlled robot.
Forensic analysis of the recovery of Wickr’s ephemeral data on Android platforms
Barton, T. and Azhar, H. 2016. Forensic analysis of the recovery of Wickr’s ephemeral data on Android platforms. in: Klemas, T. and Falk, R. (ed.) CYBER 2016 : The First International Conference on Cyber-Technologies and Cyber-Systems IARIA. pp. 35-40
Forensic analysis of secure ephemeral messaging applications on Android platforms
Azhar, H. and Barton, T. 2017. Forensic analysis of secure ephemeral messaging applications on Android platforms. in: Global Security, Safety and Sustainability - The Security Challenges of the Connected World: 11th International Conference, ICGS3 2017, London, UK, January 18-20, 2017, Proceedings Springer.
Usability and performance measure of a consumer-grade brain computer interface system for environmental control by neurological patients
Deravi, F., Ang, C., Azhar, H., Al-Wabil, A., Philips, M. and Sakel, M. 2015. Usability and performance measure of a consumer-grade brain computer interface system for environmental control by neurological patients. International Journal of Engineering and Technology Innovation (IJETI). 5 (3), pp. 165-177.
Criticality dispersion in swarms to optimize n-tuples
Azhar, H., Deravi, F. and Dimond, K. 2008. Criticality dispersion in swarms to optimize n-tuples. in: GECCO '08: Proceedings of the 10th Annual Conference on Genetic and Evolutionary Computation New York Association for Computing Machinery. pp. 1-8
Particle swarm intelligence to optimize the learning of n-tuples
Azhar, H., Deravi, F. and Dimond, K. 2008. Particle swarm intelligence to optimize the learning of n-tuples. Journal of Intelligent Systems. 17 (S), pp. 169-196. https://doi.org/10.1515/JISYS.2008.17.S1.169
Automatic identification of wildlife using local binary patterns
Azhar, H., Hoque, S. and Deravi, F. 2012. Automatic identification of wildlife using local binary patterns. in: IET Conference on Image Processing (IPR 2012) Institute of Engineering and Technology. pp. 5-11
Zoometrics - biometric identification of wildlife using natural body marks
Hoque, S., Azhar, H. and Deravi, F. 2011. Zoometrics - biometric identification of wildlife using natural body marks. International Journal of Bio-Science and Bio-Technology. 3 (3), pp. 45-53.
Forensic acquisitions of WhatsApp data on popular mobile platforms
Shortall, A. and Azhar, H. 2015. Forensic acquisitions of WhatsApp data on popular mobile platforms. in: Proceedings of the Sixth International Conference on Emerging Security Technologies IEEE. pp. 13-17