Manifold learning approach to curve identification with applications to footprint segmentation

Lokare, Namita; Ge, Qian; Snyder, Wesley E.; Jewell, Zoë C.; Allibhai, Sky; Lobatón, Edgar

doi:10.1109/cimsivp.2014.7013288

Cited by 7 publications

(2 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The pugmark census method and all the above‐mentioned track measurement methods are using recording techniques limited to two‐dimensions (2D): direct measurement, drawing on acetate sheets or taking photographs. More recently, a Microsoft Kinect depth sensor was used to capture depth images of tracks from captive tigers (Lokare et al ., ).…”

Section: Introductionmentioning

confidence: 97%

Virtual plaster cast: digital 3D modelling of lion paws and tracks using close‐range photogrammetry

2016

View full text Add to dashboard Cite

The ecological monitoring of threatened species is vital for their survival as it provides the baselines for conservation, research and management strategies. Wildlife studies using tracks are controversial mainly due to unreliable recording techniques limited to two-dimensions (2D). We assess close-range photogrammetry as a low-cost, rapid, practical and reliable field technique for the digital threedimensional (3D) modelling of lion (Panthera leo) paws and tracks. Firstly, we tested three reconstruction parameters affecting the 3D model quality. We then compared direct measurements on the paws and tracks versus the same measurements on their digital 3D models. Finally, we assessed the minimum number of photographs required for the 3D reconstruction. Masking, auto-calibration and optimisation provided higher reconstruction quality. Paws masked semi-automatically and tracks Based on the predicted error, the minimum number of photographs required for an accurate reconstruction is seven (paws) or eight (tracks) photographs. This field technique, using only a digital camera and a ruler, takes less than one minute to sample a paw or track. The introduction of the 3D facet provides more realistic replications of paws and tracks that will enable a better understanding of their intrinsic properties and variation due to external factors. This advanced recording technique will permit a refinement of the current methods aiming at identifying species, age, sex and individual from tracks.

show abstract

Section: Introductionmentioning

confidence: 97%

Virtual plaster cast: digital 3D modelling of lion paws and tracks using close‐range photogrammetry

2016

View full text Add to dashboard Cite

show abstract

“…In addition, in order to prevent the occurrence of mix-up among newborns and infants in hospitals, capturing the footprint for the infants assists the medical staff to ensure such issues will not happen [10]. However, the footprint shows some advantages of animal recognition such as stated in [11] and [12]. One of the main challenges in recognizing the animals through the footprint is the features extraction from the images, which are usually located in the boundary curve of the footprints [8].…”

Section: Introductionmentioning

confidence: 99%

Deep transfer learning for human identification based on footprint: A comparative study

Abuqadumah¹,

Ali²,

Almisreb³

et al. 2019

PEN

View full text Add to dashboard Cite

Identifying people based on their footprint has not yet gained enough attention from the researchers. Therefore, in this paper, an investigation of human identification conducted based on the footprint. Transfer Learning used as the main concept of this investigation. The aim of using Transfer Learning is to overcome the need for a large-scale dataset and achieve high accuracy with a low-scale dataset. Five well-known models used, namely, Alexnet, Vgg16, Vgg19, Googlenet, and Inception v3. Each of these models fine-tuned to fit-in the paper's topic. A dataset of 30 individuals constructed in order to train the models. The right and left footprint of each individual captured with iPhone camera. The models trained and evaluated based on the same settings. The evaluation shows that Inception v3 model achieved the highest accuracy compared to all other four models.

show abstract

Integrating AI ethics in wildlife conservation AI systems in South Africa: a review, challenges, and future research agenda

2021

View full text Add to dashboard Cite

Manifold learning approach to curve identification with applications to footprint segmentation

Cited by 7 publications

References 34 publications

Virtual plaster cast: digital 3D modelling of lion paws and tracks using close‐range photogrammetry

Virtual plaster cast: digital 3D modelling of lion paws and tracks using close‐range photogrammetry

Deep transfer learning for human identification based on footprint: A comparative study

Integrating AI ethics in wildlife conservation AI systems in South Africa: a review, challenges, and future research agenda

Contact Info

Product

Resources

About