Fingertip detection approach on depth image sequences for interactive projection system

Cadena, A.; Carvajal, Rubén; Guamán, Bruno; Granda, Roger; Peláez, Enrique; Chiluiza, Katherine

doi:10.1109/etcm.2016.7750827

Cited by 6 publications

(1 citation statement)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Xiao et al [21] go beyond the depth image to perform edge detection on the sensor's infrared (IR) stream to get hand boundaries and fingertips, then pruning touching fingertips by examining a small depth pixel neighborhood. Cadena et al [2] use depth image to first segment the arm and hand using k-means, then fingertips are detected using geometric analysis and refined based on IR edge detection as in [21]. In our work, we initially follow [20,9] but vastly extend these with data-driven segmentation and hand pose estimation, instead of a parametric approach.…”

Section: Surface Multi-touch Detectionmentioning

confidence: 99%

Enhanced Touchable Projector-depth System with Deep Hand Pose Estimation

Chai,

Shilkrot

2018

Preprint

View full text Add to dashboard Cite

Touchable projection with structured light range cameras is a prolific medium for large interaction surfaces, affording multiple simultaneous users and simple, cheap setup. However robust touch detection in such projector-depth systems is difficult to achieve due to measurement noise. We propose a novel combination of surface touch detection and a deep network for hand pose estimation, which aids in detecting both on-and above-surface hand gestures, disambiguating multiple touch fingers, as well as recovering fingertip positions in face of noisy input. We present the details of our GPU-accelerated system and an evaluation of its performance, as well as applications such as an enhanced virtual keyboard that utilizes the added features.

show abstract

Section: Surface Multi-touch Detectionmentioning

confidence: 99%