Greg Falzon
YOU?
Author Swipe
View article: Analysis and Comparison of New-Born Calf Standing and Lying Time Based on Deep Learning
Analysis and Comparison of New-Born Calf Standing and Lying Time Based on Deep Learning Open
Standing and lying are the fundamental behaviours of quadrupedal animals, and the ratio of their durations is a significant indicator of calf health. In this study, we proposed a computer vision method for non-invasively monitoring of calv…
View article: The Sentinel Bait Station: an automated, intelligent design pest animal baiting system
The Sentinel Bait Station: an automated, intelligent design pest animal baiting system Open
Context Ground baiting is a strategic method for reducing vertebrate pest populations. Best practice involves maximising bait availability to the target species, although sustaining this availability is resource intensive because baits nee…
View article: Automated Muzzle Detection and Biometric Identification via Few-Shot Deep Transfer Learning of Mixed Breed Cattle
Automated Muzzle Detection and Biometric Identification via Few-Shot Deep Transfer Learning of Mixed Breed Cattle Open
Livestock welfare and management could be greatly enhanced by the replacement of branding or ear tagging with less invasive visual biometric identification methods. Biometric identification of cattle from muzzle patterns has previously ind…
View article: The Segmented Colour Feature Extreme Learning Machine: Applications in Agricultural Robotics
The Segmented Colour Feature Extreme Learning Machine: Applications in Agricultural Robotics Open
This study presents the Segmented Colour Feature Extreme Learning Machine (SCF-ELM). The SCF-ELM is inspired by the Extreme Learning Machine (ELM) which is known for its rapid training and inference times. The ELM is therefore an ideal can…
View article: U-Infuse: Democratization of Customizable Deep Learning for Object Detection
U-Infuse: Democratization of Customizable Deep Learning for Object Detection Open
Image data is one of the primary sources of ecological data used in biodiversity conservation and management worldwide. However, classifying and interpreting large numbers of images is time and resource expensive, particularly in the conte…
View article: Automated location invariant animal detection in camera trap images using publicly available data sources
Automated location invariant animal detection in camera trap images using publicly available data sources Open
A time‐consuming challenge faced by camera trap practitioners is the extraction of meaningful data from images to inform ecological management. An increasingly popular solution is automated image classification software. However, most solu…
View article: Confluence: A Robust Non-IoU Alternative to Non-Maxima Suppression in Object Detection
Confluence: A Robust Non-IoU Alternative to Non-Maxima Suppression in Object Detection Open
Confluence is a novel non-Intersection over Union (IoU) alternative to Non-Maxima Suppression (NMS) in bounding box post-processing in object detection. It overcomes the inherent limitations of IoU-based NMS variants to provide a more stab…
View article: Automated Location Invariant Animal Detection In Camera Trap Images Using Publicly Available Data Sources
Automated Location Invariant Animal Detection In Camera Trap Images Using Publicly Available Data Sources Open
1. A time-consuming challenge faced by ecologists is the extraction of meaningful data from camera trap images to inform ecological management. Automated object detection solutions are increasingly, however, most are not sufficiently robus…
View article: How many images do I need? Understanding how sample size per class affects deep learning model performance metrics for balanced designs in autonomous wildlife monitoring
How many images do I need? Understanding how sample size per class affects deep learning model performance metrics for balanced designs in autonomous wildlife monitoring Open
Deep learning (DL) algorithms are the state of the art in automated classification of wildlife camera trap images. The challenge is that the ecologist cannot know in advance how many images per species they need to collect for model traini…
View article: How many images do I need? Understanding how sample size per class\n affects deep learning model performance metrics for balanced designs in\n autonomous wildlife monitoring
How many images do I need? Understanding how sample size per class\n affects deep learning model performance metrics for balanced designs in\n autonomous wildlife monitoring Open
Deep learning (DL) algorithms are the state of the art in automated\nclassification of wildlife camera trap images. The challenge is that the\necologist cannot know in advance how many images per species they need to\ncollect for model tra…
View article: U-Infuse: Democratization of Customizable AI for Object Detection
U-Infuse: Democratization of Customizable AI for Object Detection Open
Summary Image data is one of the primary sources of ecological data used in biodiversity conservation and management worldwide. However, classifying and interpreting large numbers of images is time and resource expensive, particularly in t…
View article: Location Invariant Animal Recognition Using Mixed Source Datasets and Deep Learning
Location Invariant Animal Recognition Using Mixed Source Datasets and Deep Learning Open
A time-consuming challenge faced by camera trap practitioners all over the world is the extraction of meaningful data from images to inform ecological management. The primary methods of image processing used by practitioners includes manua…
View article: Livestock classification and counting in quadcopter aerial images using Mask R-CNN
Livestock classification and counting in quadcopter aerial images using Mask R-CNN Open
Quadcopters equipped with machine learning vision systems are bound to become an essential technique for precision agriculture applications in pastures in the near future. This paper presents a low-cost approach for livestock counting join…
View article: Automated cattle counting using Mask R-CNN in quadcopter vision system
Automated cattle counting using Mask R-CNN in quadcopter vision system Open
The accurate and reliable counting of animals in quadcopter acquired imagery is one of the most promising but challenging tasks in intelligent livestock management in the future. In this paper we demonstrate the application of the cutting-…
View article: ClassifyMe: A Field-Scouting Software for the Identification of Wildlife in Camera Trap Images
ClassifyMe: A Field-Scouting Software for the Identification of Wildlife in Camera Trap Images Open
We present ClassifyMe a software tool for the automated identification of animal species from camera trap images. ClassifyMe is intended to be used by ecologists both in the field and in the office. Users can download a pre-trained model s…
View article: <i>ClassifyMe</i>: a field-scouting software for the identification of wildlife in camera trap images
<i>ClassifyMe</i>: a field-scouting software for the identification of wildlife in camera trap images Open
We present ClassifyMe a software tool for the automated identification of animal species from camera trap images. ClassifyMe is intended to be used by ecologists both in the field and in the office. Users can download a pre-trained model s…
View article: Livestock vocalisation classification in farm soundscapes
Livestock vocalisation classification in farm soundscapes Open
Livestock vocalisations have been shown to contain information related to animal welfare and behaviour. Automated sound detection has the potential to facilitate a continuous acoustic monitoring system, for use in a range Precision Livesto…
View article: OpenCL Performance Prediction using Architecture-Independent Features
OpenCL Performance Prediction using Architecture-Independent Features Open
OpenCL is an attractive model for heterogeneous high-performance computing systems, with wide support from hardware vendors and significant performance portability. To support efficient scheduling on HPC systems it is necessary to perform …
View article: Hardware And Embedded Algorithms For Real Time Variable Rate Fertiliser Applications
Hardware And Embedded Algorithms For Real Time Variable Rate Fertiliser Applications Open
Efficient use of fertilisers, in particular the use of Nitrogen (N), is one of the rate-limiting factors in meeting global food production requirements. While N is a key driver in increasing crop yields, overuse can also lead to negative e…
View article: Fast Object Detection In Pastoral Landscapes Using A Multiple Expert Colour Feature Extreme Learning Machine
Fast Object Detection In Pastoral Landscapes Using A Multiple Expert Colour Feature Extreme Learning Machine Open
Fast and accurate object detection is a desire of many vision-guided robotics based systems. Agriculture is an area where detection accuracy is often sacrificed for speed, especially in the pursuit of real time results. Pastoral landscapes…
View article: Sound Analysis And Detection, And The Potential For Precision Livestock Farming - A Sheep Vocalization Case Study
Sound Analysis And Detection, And The Potential For Precision Livestock Farming - A Sheep Vocalization Case Study Open
Livestock vocalizations contain a wealth of information pertaining to welfare state and behaviour. Acoustic monitoring is non-invasive and has potential for numerous Precision Livestock Farming (PLF) applications. A key step in the develop…
View article: The higher you go the less you will know: placing camera traps high to avoid theft will affect detection
The higher you go the less you will know: placing camera traps high to avoid theft will affect detection Open
Vandalism and theft of camera traps is common, imposing financial and data losses on wildlife professionals. Like many 'victims', our response to a spate of thefts was to attempt to install camera traps at heights we suspected would reduce…
View article: Are we getting the full picture? Animal responses to camera traps and implications for predator studies
Are we getting the full picture? Animal responses to camera traps and implications for predator studies Open
Camera trapping is widely used in ecological studies. It is often considered nonintrusive simply because animals are not captured or handled. However, the emission of light and sound from camera traps can be intrusive. We evaluated the day…
View article: Ultrasonic outputs from five camera trap models including two control recordings, two ANABAT directions were utilised (directly in front and offset 45 degrees to the central axis of the camera).
Ultrasonic outputs from five camera trap models including two control recordings, two ANABAT directions were utilised (directly in front and offset 45 degrees to the central axis of the camera). Open
Ultrasonic outputs from five camera trap models including two control recordings, two ANABAT directions were utilised (directly in front and offset 45 degrees to the central axis of the camera).