Hand Gesture Recognition in Automotive Human–Machine Interaction Using Depth Cameras

Zengeler, Nico; Kopinski, Thomas; Handmann, Uwe

doi:10.3390/s19010059

Cited by 67 publications

(32 citation statements)

References 67 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Far better results could be reached with a time of flight (ToF) distance sensor, which is typically used as a scanning device [12][13][14][15] rang finder [16][17][18] and gesture detection sensor [19]. The used VL53L0X module is capable of capturing distances up to a maximum range of 2 m with a very high accuracy.…”

Section: Combination Of the Sensorsmentioning

confidence: 99%

Development of a Sensor to Measure Physician Consultation Times

Gabl

Stummer

2019

Sensors

View full text Add to dashboard Cite

The duration of patient–physician contact is an important factor for the optimisation of treatment processes in healthcare systems. Available methods can be labour-intensive and the quality is, in many cases, poor. A part of this research project is to develop a sensor system, which allows the detection of people passing through a door, including the direction. For this purpose, two time of flight sensors are combined with a door sensor and a motion detection sensor (for redundancy) on one single side of the door frame. The period between two single measurements could be reduced to 50 ms, which allows the measurement of walking speed up to 2 ms − 1 . The accuracy of the time stamp for each event is less than one second and ensures a precise documentation of the consultation time. This paper presents the development of the sensor system, the miniaturisation of the installation and first measurement results, as well as the measurement’s concept of quality analysis, including multiple door applications. In future steps, the sensor system will be deployed at different medical practices to determine the exact duration of the patient–physician interaction over a longer time period.

show abstract

Section: Combination Of the Sensorsmentioning

confidence: 99%

Development of a Sensor to Measure Physician Consultation Times

Gabl

Stummer

2019

Sensors

View full text Add to dashboard Cite

show abstract

“…Recently, HGR systems using vision-based interaction and control have become more common [ 1 , 2 , 3 ], and they are, compared to the conventional inputs of mouse and keyboard, more natural because of the intuitiveness of hand gestures. Therefore, HGR dominates a wide range of applications in the automotive sector, consumer electronics, home automation, and others [ 3 , 4 , 5 , 6 ]. An essential feature for these applications is real-time performance, so that HGR systems must be designed to give feedback with no lag to the gestures that users may input.…”

Section: Introductionmentioning

confidence: 99%

Improving Real-Time Hand Gesture Recognition with Semantic Segmentation

Benitez-Garcia

Prudente-Tixteco

Castro-Madrid

et al. 2021

Sensors

View full text Add to dashboard Cite

Hand gesture recognition (HGR) takes a central role in human–computer interaction, covering a wide range of applications in the automotive sector, consumer electronics, home automation, and others. In recent years, accurate and efficient deep learning models have been proposed for real-time applications. However, the most accurate approaches tend to employ multiple modalities derived from RGB input frames, such as optical flow. This practice limits real-time performance due to intense extra computational cost. In this paper, we avoid the optical flow computation by proposing a real-time hand gesture recognition method based on RGB frames combined with hand segmentation masks. We employ a light-weight semantic segmentation method (FASSD-Net) to boost the accuracy of two efficient HGR methods: Temporal Segment Networks (TSN) and Temporal Shift Modules (TSM). We demonstrate the efficiency of the proposal on our IPN Hand dataset, which includes thirteen different gestures focused on interaction with touchless screens. The experimental results show that our approach significantly overcomes the accuracy of the original TSN and TSM algorithms by keeping real-time performance.

show abstract

“…The overall goal is to understand the body language and then create more functional and efficient human-computer interfaces. Application areas are vast; from driver support via hand-controlled cockpit elements [2], through to home automation with consumer electronics driven by gestures [3], gaming industry applications [4], interaction with virtual objects [5], and finally, technological support for people with disabilities [6]. Solutions available on the market are either limited, very simple, or have background and illumination requirements that are difficult to meet in real-life scenarios.…”

Section: Introductionmentioning

confidence: 99%

Hand Posture Recognition Using Skeletal Data and Distance Descriptor

Kapuściński

Warchoł

2020

Applied Sciences

View full text Add to dashboard Cite

In this paper, a method for the recognition of static hand postures based on skeletal data was presented. A novel descriptor was proposed. It encodes information about distances between particular hand points. Five different classifiers were tested, including four common methods and a proposed modification of nearest neighbor classifier, which can distinguish between posture classes differing mostly in hand orientation. The experiments were performed using three challenging datasets of gestures from Polish and American Sign Languages. The proposed method was compared with other approaches found in the literature. It outperforms every compared method, including our previous work, in terms of recognition rate.

show abstract

Hand Gesture Recognition in Automotive Human–Machine Interaction Using Depth Cameras

Cited by 67 publications

References 67 publications

Development of a Sensor to Measure Physician Consultation Times

Development of a Sensor to Measure Physician Consultation Times

Improving Real-Time Hand Gesture Recognition with Semantic Segmentation

Hand Posture Recognition Using Skeletal Data and Distance Descriptor

Contact Info

Product

Resources

About