Mark Hansen's Outputs (25)

Machine vision and deep learning for robotic harvesting of shiitake mushrooms (2025)
Presentation / Conference Contribution

There is a substantial requirement for the modernisation of our agricultural practices. Current methods can be susceptible to labour shortages, damaging to the environment, and inefficient; and these factors can lead to food wastage so threatening fo... Read More about Machine vision and deep learning for robotic harvesting of shiitake mushrooms.

Achieving goals using reward shaping and curriculum learning (2023)
Presentation / Conference Contribution

Real-time control for robotics is a popular research area in the reinforcement learning community. Through the use of techniques such as reward shaping, researchers have managed to train online agents across a multitude of domains. Despite these adva... Read More about Achieving goals using reward shaping and curriculum learning.

Airborne Microplastics measurement: Putting people at the heart of the science (2023)
Presentation / Conference Contribution

Transformers and human-robot interaction for delirium detection (2023)
Presentation / Conference Contribution

An estimated 20% of patients admitted to hospital wards are affected by delirium. Early detection is recommended to treat underlying causes of delirium, however workforce strain in general wards often causes it to remain undetected. This work propose... Read More about Transformers and human-robot interaction for delirium detection.

A procedure for monitoring the phenological status of peach flowers with artificial vision (2022)
Presentation / Conference Contribution

Tree flowering is a major event in crop production as it anticipates season yield. However a number of issues may occur during the campaign such as frost, and/or irregular mineral nutrition, among other, that strongly affect this process. On the othe... Read More about A procedure for monitoring the phenological status of peach flowers with artificial vision.

Vision based semantic runway segmentation from simulation with deep convolutional neural networks (2021)
Presentation / Conference Contribution

Manned flight crew rely upon optical imagery to make sense of the world and carry out high level guidance, navigation & control tasks. To advance autonomous aircraft’s capabilities and safety, programmes need to be developed that aim to achieve pilot... Read More about Vision based semantic runway segmentation from simulation with deep convolutional neural networks.

Contactless robust 3D palm-print identification using photometric stereo (2021)
Presentation / Conference Contribution

Palmprints are of considerable interest as a reliable biometric, since they offer significant advantages, such as greater user acceptance than fingerprint or iris recognition. 2D systems can be spoofed by a photograph of a hand; however, 3D avoids th... Read More about Contactless robust 3D palm-print identification using photometric stereo.

Shedding smart light on the effectiveness of chemotherapy: using Raman spectroscopy and machine learning to differentiate the effects of Cytarabine toxicity and crosstalk of leukaemic and bone marrow stromal cells (2021)
Presentation / Conference Contribution

Mesenchymal stromal cells (MSC) protect leukaemic cells from drug-induced toxicity within the bone marrow niche, with increasing evidence of leukaemic impact on supportive stroma. The nucleoside analogue, cytarabine (ara-C), is a front-line agent for... Read More about Shedding smart light on the effectiveness of chemotherapy: using Raman spectroscopy and machine learning to differentiate the effects of Cytarabine toxicity and crosstalk of leukaemic and bone marrow stromal cells.

Reinforcement learning for a perched landing in the presence of wind (2021)
Presentation / Conference Contribution

Previous research by the University of Bristol's Flight Lab demonstrated the feasibility of using reinforcement learning to generate a controller to perform an agile perched landing flight manoeuvre. However, flight testing demonstrated the limits of... Read More about Reinforcement learning for a perched landing in the presence of wind.

Weed classification in grasslands using convolutional neural networks (2019)
Presentation / Conference Contribution

Automatic identification and selective spraying of weeds (such as dock) in grass can provide very significant long-term ecological and cost benefits. Although machine vision (with interface to suitable automation) provides an effective means of achie... Read More about Weed classification in grasslands using convolutional neural networks.

Surface normals based landmarking for 3D face recognition using photometric stereo captures (2019)
Presentation / Conference Contribution

In recent decades, many 3D data acquisition methods have been developed to provide accurate and cost-effective 3D captures of the human face. An example system, which can accommodate both research and commercial applications, is the Photoface device.... Read More about Surface normals based landmarking for 3D face recognition using photometric stereo captures.

Broad-leaf weed detection in pasture (2018)
Presentation / Conference Contribution

Weed control in pasture is a challenging problem that can be expensive and environmentally unfriendly. This paper proposes a novel method for recognition of broad-leaf weeds in pasture such that precision weed control can be achieved with reduced her... Read More about Broad-leaf weed detection in pasture.

Multispectral contactless 3D handprint acquisition for identification (2018)
Presentation / Conference Contribution

We present and experimentally demonstrate the potential effectiveness of a photometric stereo based high resolution system for capturing 3D handprints using visible light sources. The sub-surface vascular structures are also enhanced through the use... Read More about Multispectral contactless 3D handprint acquisition for identification.

Locomotion traits of dairy cows from overhead three-dimensional video (2016)
Presentation / Conference Contribution

We investigate two locomotion traits in dairy cows from overhead 3D video to observe lameness trends. Detecting lameness -particularly at an early stage- is important in order to allow early treatment which maximizes detection benefits. The proposed... Read More about Locomotion traits of dairy cows from overhead three-dimensional video.

Overhead spine arch analysis of dairy cows from three-dimensional video (2016)
Presentation / Conference Contribution

We present a spine arch analysis method in dairy cows using overhead 3D video data. This method is aimed for early stage lameness detection. That is important in order to allow early treatment; and thus, reduce the animal suffering and minimize the h... Read More about Overhead spine arch analysis of dairy cows from three-dimensional video.

Quadruped locomotion analysis using three-dimensional video (2016)
Presentation / Conference Contribution

Abstract— To date, there has not been a single method
suitable for large-scale or regular-basis implementation to analyze the locomotion of quadruped animals. Existing methods are not sensitive enough for detecting minor deviations from healthy gait... Read More about Quadruped locomotion analysis using three-dimensional video.

Non-intrusive automated measurement of dairy cow body condition using 3D video (2015)
Presentation / Conference Contribution

Regular scoring of a dairy herd in terms of various physical metrics such as Body Condition Score (BCS), mobility and weight are essential for maintaining high animal welfare. This paper presents preliminary results of an automated system capable of... Read More about Non-intrusive automated measurement of dairy cow body condition using 3D video.

Long-range concealed object detection through active covert illumination (2015)
Presentation / Conference Contribution

© 2015 SPIE. When capturing a scene for surveillance, the addition of rich 3D data can dramatically improve the accuracy of object detection or face recognition. Traditional 3D techniques, such as geometric stereo, only provide a coarse grained recon... Read More about Long-range concealed object detection through active covert illumination.

BRDF estimation for faces from a sparse dataset using a neural network (2013)
Presentation / Conference Contribution

We present a novel �ve source near-infrared photometric
stereo 3D face capture device. The accuracy of the system is demonstrated by a comparison with ground truth from a commercial 3D scanner. We also use the data from the �ve captured images to mo... Read More about BRDF estimation for faces from a sparse dataset using a neural network.

Twins 3D face recognition challenge (2011)
Presentation / Conference Contribution

Existing 3D face recognition algorithms have achieved high enough performances against public datasets like FRGC v2, that it is difficult to achieve further significant increases in recognition performance. However, the 3D TEC dataset is a more chall... Read More about Twins 3D face recognition challenge.