Semantic human activity annotation tool using skeletonized surveillance videos

Lee, Bokyung; Lee, Michael; Zhang, Pan; Tessier, Alexander; Khan, Azam

doi:10.1145/3341162.3343807

Cited by 7 publications

(2 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Lastly, labelling individual instances of a class can add further meaning to an image description. This can be useful for surveillance to identify individuals (Lee et al, 2019). See Figure 3 for an overview of the semantic concepts.…”

Section: Semantic Expressivenessmentioning

confidence: 99%

A survey of image labelling for computer vision applications

Sager

Janiesch

Zschech

2021

Journal of Business Analytics

View full text Add to dashboard Cite

Supervised machine learning methods for image analysis require large amounts of labelled training data to solve computer vision problems. The recent rise of deep learning algorithms for recognising image content has led to the emergence of many ad-hoc labelling tools. With this survey, we capture and systematise the commonalities as well as the distinctions between existing image labelling software. We perform a structured literature review to compile the underlying concepts and features of image labelling software such as annotation expressiveness and degree of automation. We structure the manual labelling task by its organisation of work, user interface design options, and user support techniques to derive a systematisation schema for this survey. Applying it to available software and the body of literature, enabled us to uncover several application archetypes and key domains such as image retrieval or instance identification in healthcare or television.

show abstract

Section: Semantic Expressivenessmentioning

confidence: 99%

A survey of image labelling for computer vision applications

Sager

Janiesch

Zschech

2021

Journal of Business Analytics

View full text Add to dashboard Cite

show abstract

“…When employing computer vision for identification of the type of load and its position on a specified 2D surface plane on the structure, a multitude of image processing techniques such as background removal [4], heat source detection [2] and skeletonizing people [17] are available. Thermal imaging cameras can have a dual purpose: capture distributed bridge temperature and locate traffic load (i.e., pedestrians) [2,18].…”

Section: Generate Structural Displacementsmentioning

confidence: 99%

Characterizing Footbridge Response from Cyclist Crossings with Computer Vision-Based Monitoring

Kromanis

2021

Lecture Notes in Civil Engineering

View full text Add to dashboard Cite

Computer vision applications are frequently selected for short-term monitoring of bridges. The availability of high resolution and frame rate consumer-grade cameras such as action cameras makes the computer vision-based monitoring an attractive and affordable option. This paper presents findings from monitoring deformations of a steel girder footbridge subjected to cyclist loads captured with an action camera. A modified GoPro action camera with a zoom lens was located 35 m from the centre of the bridge. High resolution (720 × 1080 pixel) and high frame rate (240 fps) videos were recorded during cyclist crossings. Image processing, measurement denoising, vertical deflection interpretation and influence line (bridge signature) derivations are presented and discussed. Both static and dynamic responses are identifiable (discernible in vision measurements) and even tiny (a fraction of a millimetre) vertical deflections can be accurately computed from videos collected with the action camera.

show abstract