Nick Wright
Nick Wright has a total of 15 co-authors. Here are the top co-authors by number of shared publications:
A. Stephen McGough
School of Computing
3 shared publications- Cameron Trotter
School of Engineering † School of Computing ‡ School of Natural & Environmental Sciences Newcastle University UK
2 shared publications - Georgia Atkinson
School of Engineering
2 shared publications - Matt Sharpe
School of Natural and Environmental Sciences Newcastle University Newcastle upon Tyne UK
2 shared publications - Per Berggren
School of Natural and Environmental Sciences Newcastle University Newcastle upon Tyne UK
2 shared publications - Alton Horsfall
Sch. of Electr., Electron. & Comput. Eng., Newcastle Univ., UK
1 shared publication
Latest Publications
- Open Access
The Effects of Signal-to-Noise Ratio on Generative Adversarial Networks Applied to Marine Bioacoustic Data
In recent years generative adversarial networks (GANs) have been used to supplement datasets within the field of marine bioacoustics. This is driven by factors such as the cost to collect data, data sparsity and aid preprocessing. One notable challenge with marine bioacoustic data is the low signal-to-noise ratio (SNR) posing difficulty when applying deep learning techniques such as GANs. This work investigates the effect SNR has on the audio-based GAN performance and examines three different evaluation methodologies for GAN performance, yielding interesting results on the effects of SNR on GANs, specifically WaveGAN.
Open AccessThe Effects of Signal-to-Noise Ratio on Generative Adversarial Networks Applied to Marine Bioacoustic Data
In recent years generative adversarial networks (GANs) have been used to supplement datasets within the field of marine bioacoustics. This is driven by factors such as the cost to collect data, data sparsity and aid preprocessing. One notable challenge with marine bioacoustic data is the low signal-to-noise ratio (SNR) posing difficulty when applying deep learning techniques such as GANs. This work investigates the effect SNR has on the audio-based GAN performance and examines three different evaluation methodologies for GAN performance, yielding interesting results on the effects of SNR on GANs, specifically WaveGAN.
- Open Access
Towards Automatic Cetacean Photo-Identification: A Framework for Fine-Grain, Few-Shot Learning in Marine Ecology
Photo-identification (photo-id) is one of the main non-invasive capture-recapture methods utilised by marine researchers for monitoring cetacean (dolphin, whale, and porpoise) populations. This method has historically been performed manually resulting in high workload and cost due to the vast number of images collected. Recently automated aids have been developed to help speed-up photo-id, although they are often disjoint in their processing and do not utilise all available identifying information. Work presented in this paper aims to create a fully automatic photo-id aid capable of providing most likely matches based on all available information without the need for data pre-processing such as cropping. This is achieved through a pipeline of computer vision models and post-processing techniques aimed at detecting cetaceans in unedited field imagery before passing them downstream for individual level catalogue matching. The system is capable of handling previously uncatalogued individuals and flagging these for investigation thanks to catalogue similarity comparison. We evaluate the system against multiple real-life photo-id catalogues, achieving mAP@IOU[0.5] = 0.91, 0.96 for the task of dorsal fin detection on catalogues from Tanzania and the UK respectively and 83.1, 97.5% top-10 accuracy for the task of individual classification on catalogues from the UK and USA.
Open AccessTowards Automatic Cetacean Photo-Identification: A Framework for Fine-Grain, Few-Shot Learning in Marine Ecology
Photo-identification (photo-id) is one of the main non-invasive capture-recapture methods utilised by marine researchers for monitoring cetacean (dolphin, whale, and porpoise) populations. This method has historically been performed manually resulting in high workload and cost due to the vast number of images collected. Recently automated aids have been developed to help speed-up photo-id, although they are often disjoint in their processing and do not utilise all available identifying information. Work presented in this paper aims to create a fully automatic photo-id aid capable of providing most likely matches based on all available information without the need for data pre-processing such as cropping. This is achieved through a pipeline of computer vision models and post-processing techniques aimed at detecting cetaceans in unedited field imagery before passing them downstream for individual level catalogue matching. The system is capable of handling previously uncatalogued individuals and flagging these for investigation thanks to catalogue similarity comparison. We evaluate the system against multiple real-life photo-id catalogues, achieving mAP@IOU[0.5] = 0.91, 0.96 for the task of dorsal fin detection on catalogues from Tanzania and the UK respectively and 83.1, 97.5% top-10 accuracy for the task of individual classification on catalogues from the UK and USA.
- Open Access
NDD20: A large-scale few-shot dolphin dataset for coarse and fine-grained categorisation
We introduce the Northumberland Dolphin Dataset 2020 (NDD20), a challenging image dataset annotated for both coarse and fine-grained instance segmentation and categorisation. This dataset, the first release of the NDD, was created in response to the rapid expansion of computer vision into conservation research and the production of field-deployable systems suited to extreme environmental conditions -- an area with few open source datasets. NDD20 contains a large collection of above and below water images of two different dolphin species for traditional coarse and fine-grained segmentation. All data contained in NDD20 was obtained via manual collection in the North Sea around the Northumberland coastline, UK. We present experimentation using standard deep learning network architecture trained using NDD20 and report baselines results.
Open AccessNDD20: A large-scale few-shot dolphin dataset for coarse and fine-grained categorisation
We introduce the Northumberland Dolphin Dataset 2020 (NDD20), a challenging image dataset annotated for both coarse and fine-grained instance segmentation and categorisation. This dataset, the first release of the NDD, was created in response to the rapid expansion of computer vision into conservation research and the production of field-deployable systems suited to extreme environmental conditions -- an area with few open source datasets. NDD20 contains a large collection of above and below water images of two different dolphin species for traditional coarse and fine-grained segmentation. All data contained in NDD20 was obtained via manual collection in the North Sea around the Northumberland coastline, UK. We present experimentation using standard deep learning network architecture trained using NDD20 and report baselines results.
- Open Access
- 13 June 2018
- Published by IntechOpen
Self-Oscillatory DC-DC Converter Circuits for Energy Harvesting in Extreme Environments
A novel self-starting converter circuit technology is described for energy harvesting and powering wireless sensor nodes, constructed from silicon carbide devices and proprietary high temperature passives for deployment in hostile environments. After a brief review of the advantages using Silicon Carbide (SiC) over other semiconductors in extreme environments, the chapter will describe the advantages and principles when designing circuitry and architectures using SiC for power electronics. The practical results from a novel self-starting DC-DC converter are reported, which is designed to supply power to a WSN for deployment in high temperature environments. The converter operates in the boundary between continuous and discontinuous mode of operation and has a Voltage Conversion Ratio (VCR) of 3 at 300°C. This topology is able to self-start and so requires no external control circuitry, making it ideal for energy harvesting applications, where the energy supply may be intermittent. Experimental results for the self-starting converter operating from room temperature up to 300°C are presented. The converter output voltage, switching frequency, total power loss and efficiency were presented at temperatures up to 300°C.
- 13 June 2018
- Published by IntechOpen
Open AccessSelf-Oscillatory DC-DC Converter Circuits for Energy Harvesting in Extreme Environments
A novel self-starting converter circuit technology is described for energy harvesting and powering wireless sensor nodes, constructed from silicon carbide devices and proprietary high temperature passives for deployment in hostile environments. After a brief review of the advantages using Silicon Carbide (SiC) over other semiconductors in extreme environments, the chapter will describe the advantages and principles when designing circuitry and architectures using SiC for power electronics. The practical results from a novel self-starting DC-DC converter are reported, which is designed to supply power to a WSN for deployment in high temperature environments. The converter operates in the boundary between continuous and discontinuous mode of operation and has a Voltage Conversion Ratio (VCR) of 3 at 300°C. This topology is able to self-start and so requires no external control circuitry, making it ideal for energy harvesting applications, where the energy supply may be intermittent. Experimental results for the self-starting converter operating from room temperature up to 300°C are presented. The converter output voltage, switching frequency, total power loss and efficiency were presented at temperatures up to 300°C.