United States

Hand pose estimation is getting a lot of attention in many areas such
as Human-Computer Interaction and Sign Language Recognition.
A fundamental step to accurately estimate the hand pose involves
detecting and localizing fingertips in an image. Despite the progress
of 2-D hand pose estimation in recent studies, accurate and robust
detection and localization of fingertips still remains a challenging
task due to low resolution of a fingertip in images and varying
lightning condition.
Inspired by the progress of the Generative Adversarial Network
(GAN) and image-style transfer, we propose a two-stage pipeline to
accurately localize the fingertip position even in varying lighting
and severe self occlusion on depth images. The idea is to use a
Cycle-consistent Generative Adversarial Network (Cycle-GAN) to
apply unpaired image-to-image translation and generate a depth
image with colored predictions on the fingertips, wrist, and palm
given a real depth image. The model is trained in a semi-supervised
manner using a collection of images from source and target domains
that do not need to be related in anyway. Then, by applying color
segmentation techniques, we localize the center of each colored area
which results in finding the location of each fingertip along with
center of the wrist and the palm. The proposed method achieves
visually promising results on noisy depth images captured using the
Microsoft Kinect. Experiments on the challenging NYU hand dataset
have demonstrated that our approach not only generates plausible
samples, but also outperforms state-of-the-art approaches on 2-D
fingertip estimation by a significant margin even in the presence
of severe self-occlusion and varying lighting conditions. Moreover,
fingertips would be detected irrespective of user orientation using
this method.

PETRA 2021

A pipeline for Hand 2-D Keypoint Localization using Unpaired Image to Image Translation

fingertip detection and localization

2d hand pose estimation

human-computer interaction

generative adversarial networks

domain transfer

ICPR 2020 is the premier international conference on Pattern Recognition, gathering leading researchers from around the world to present their latest achievements in Pattern Analysis and Recognition, applied Artificial Intelligence and Machine Learning. The topic of the year is " Putting Artificial intelligence to work on Patterns". 
For the first time, ICPR has employed a two-round review process similar to journal submissions, with new papers allowed to be submitted in either the first or second round and papers submitted in the first round and not accepted allowed to be revised and re-submitted for second round review. 

In this edition of the **ICPR 2020** Conference, there are 1407 Oral/Poster presentations organized in five Tracks: 
- Artificial Intelligence, Machine Learning for Pattern Analysis; 
- Biometrics, Human Analysis and Behavior Understanding; Computer Vision, Robotics and Intelligent Systems; 
- Document and Media Analysis; and 
- Image and Signal Processing. 

The **ICPR 2020** Main Conference program also includes 7 Keynotes from prominent world-renowned scientists, 8 Tutorials, 28 Demos, 8 Challenges, 2 Panels, as well as an Industry/Sponsor Exhibition. In addition, 41 Workshops on a range of important current and emerging research topics complete the ICPR 2020 program. 


ICPR 2020

technical paper

**About**
 The PErvasive Technologies Related to Assistive Environments (PETRA) conference is a highly interdisciplinary conference that focuses on computational and engineering approaches to improve the quality of life and enhance human performance in a wide range of settings, in the workplace, at home, in public spaces, urban environments, and other. Outcomes of this conference have a broad impact in application areas that include, manufacturing, transportation, healthcare, energy systems, security and safety, robotics, biomedicine, environment and conservation, and many others. PETRA brings together very different types of technologies to also address important social and healthcare issues for sensitive populations, such as the elderly, persons suffering from chronic conditions such as Alzheimer’s, Parkinson’s, Cerebral Palsy, and other disabilities or traumas.

 PETRA (which means “stone” in Greek) addresses important human living needs. From a technological perspective, PETRA motivates and inspires new scientific thrusts, innovations and discoveries to improve living environments, a particularly important issue, in an increasingly crowded and complex world where the need for inclusiveness and connectivity with the rest of the world is key. For the elderly in particular, PETRA addresses the fact that, as people grow older; they will increasingly rely on technology to be able to prolong staying in their homes and enjoy an independent life.

 The PETRA 2021 proceedings will be published in the ACM Digital Library as part of the ACM ICPS program. The ISBN number assigned to PETRA '21 is 978-1-4503-8792-7

The PErvasive Technologies Related to Assistive Environments (PETRA) conference is a highly interdisciplinary conference that focuses on computational and engineering approaches to improve the quality of life and enhance human performance in a wide range of settings, in the workplace, at home, in public spaces, urban environments, and other. Outcomes of this conference have a broad impact in application areas that include, manufacturing, transportation, healthcare, energy systems, security and safety, robotics, biomedicine, environment and conservation, and many others. PETRA brings together very different types of technologies to also address important social and healthcare issues for sensitive populations, such as the elderly, persons suffering from chronic conditions such as Alzheimer’s, Parkinson’s, Cerebral Palsy, and other disabilities or traumas.

In this presentation, we propose Structurally Guided Channel Attention Networks (SGCA-Net), a principled way to guide the channel at- tention of CNNs. Convolution operator constructs features maps by using both channel and spatial information within the receptive fields of its filters. Prior research has investigated the impact of strengthening the representational power of CNNs using channel attention modules. In this work, we guide the channel attention of networks using feature vectors that contain clinically relevant information. We do so by attaching guided attention modules into a state-of-the-art network architecture, and guiding these attention modules with domain knowledge using feature vectors. Experi- ments on a dataset of 5512 posterior retinal images, taken using a wide angle fundus camera, show that SGCA-Net achieves 0.983 and 0.948 AUC to predict plus and normal categories, respectively. SGCA-Net achieves higher performance than CNNs without atten- tion modules and CNNs with unguided attention modules.

Structurally Guided Channel Attention Networks: SGCA-Net

Currently there is much research in the area of person identification. Mostly it is based on multi-biometric data. In this paper, we aim to leverage soft biometric properties to achieve person reidentification by using unobtrusive sensors, envisioning assistive environments, which recognize their user and thus automatically personalize and adapt. In practice, a car seat recognizes the person
who sits down and greets the person with their own name, enabling various customisation in the car unique to the user, like seat configurations.
We present a system composed of a sensor equipped car seat, which is able to recognize a person from a predefined group. We contribute two classification approaches based on cosine similarity measure and on triplet loss learning. These are thoroughly analysed and evaluated in a user study with nine participants. We achieve the best re-identification performance using a hand-crafted feature approach based on the comparing measure of cosine similarity combined with majority voting. The highest overall precision achieved in re-identifying a person from a group of nine users is 80 %.

Person Re-Identification in a Car Seat: Comparison of Cosine Similarity and Triplet Loss based approaches on Capacitive Proximity Sensing data

People with severe motor impairment oftentimes rely on unconventional assistive interfaces to complete daily activities. In this work, we developed a holistic shared control framework to help them achieve fast and accurate indoor navigation using low throughput human machine interfaces.
Based off our previously developed shared position control method,
we added orientation control, action control, and a state machine architecture to create the new framework NOVELTI 2.0.
The framework provides generic support for various LTIs. We validated the framework using Emotiv EPOC headset and a single-switch interface.
A comprehensive comparative study involving 10 human subjects navigating a wheelchair in a real indoor environment demonstrated that our framework could 
achieve high navigation accuracy about 0.05 m for position and 5 degrees for orientation.
Compared to steering control, our method required half the navigation time and half the number of commands in routes longer than 20 m.
The NASA TLX survey results also indicated lower subjective workload with our method.
Experimental data is provided for download and future evaluation.

NOVELTI2.0: Enhanced Assistive Robot Navigation with Low Throughput Interfaces

n this paper, we present a novel method to learn end-to-end vi-suomotor policies for robotic manipulators. The method computesstate-action mappings in a supervised learning manner from videodemonstrations and robot trajectories. We show that the robotlearns to perform different tasks by associating image features withthe corresponding movement primitives of different grasp poses.To evaluate the effectiveness of the proposed learning method, weconduct experiments with a PR2 robot in a simulation environment.The purpose of these experiments is to evaluate the system’s abilityto perform manipulation tasks

Learning Visuomotor Policies with Deep Movement Primitives

We present a perspective of the role of participatory design in Human-Robot Collaboration (HRC) for People with Motor Disabilities (PWMD). We have been involved in several multiyear projects related to HRC for PWMD, where we encountered different challenges related to planning and participation, preferences of stakeholders, using certain participatory design techniques, technology exposure, as well as, ethical legal and social implications. These challenges helped us provide five lessons learned that could guide researchers when using participatory design with vulnerable groups. In particular, early-career researchers who start exploring research in HRC for people with disabilities.

Reflecting upon Participatory Design in Human-Robot Collaboration for People with Motor Disabilities: Challenges and Lessons Learned from Three Multiyear Projects

This paper presents a design concept for affordable exoskeletons without
renouncing to advanced interaction control modalities based on force
control technologies. Affordability is reached by (1) lowering the
motor requirements, thanks to a smart mechanical design, (2) lowering
the sensing requirements, thanks to extensive use of microprocessor
DMA, and (3) using low-cost computational platforms. A main finding
of this work is that by lowering the motor requirements the exoskeleton
improves its inherent force controllability.

Toward Personal Affordable Exoskeletons With Force Control Capabilities

This work presents the development of a child-robot interaction(CRI) system for edutainment scenarios, aiming to provide a framework for their design and to simplify access to social robots by educators with non-specialized technical knowledge in this challenging area. Our framework incorporates powerful robotic perception modules for action and emotion recognition of the interacting child, allowing the robot to exhibit empathy and be informed of the child’s activity. Both developed modules are evaluated on respective datasets, outperforming the current state-of-the-art by a significant margin, while retaining low computational cost. The modules are complemented by off-the-shelf automatic speech recognition and synthesis components to further enable and enrich edutainmment-focused CRI. Moreover, the developed framework allows custom CRI scenario-building via a suitable graphical user interface, providing a valuable asset to educators wishing to utilize social robots in the classroom.

A robotic edutainment framework for designing child-robot interaction scenarios

As mobile technologies have become ubiquitous in recent years, computer-based cognitive tests have become more popular and efficient. In this work, we focus on assessing motor function in children by analyzing their gait movements. Although there has been a lot of research on designing automated assessment systems for gait analysis, most of these efforts use obtrusive wearable sensors for measuring body movements. We have devised a computer vision-based assessment system that only requires a camera which makes it easier to employ in school or home environments. A dataset has been created with 27 children performing the test. Furthermore in order to improve the accuracy of the system, a deep learning based model was pre-trained on NTU-RGB+D 120 dataset and then it was fine-tuned on our gait dataset. The results highlight the efficacy of proposed work for automating the assessment of children's performances by achieving 76.61% classification accuracy.

Automated system to measure Tandem Gait to assess executive functions in children

This article proposes a novel approach for augmenting generative adversarial network (GAN) with a self-supervised task in order to improve its ability for encoding video representations that are useful in downstream tasks such as human activity recognition. In the proposed method, input video frames are randomly transformed by different spatial transformations, such as rotation, translation and shearing or temporal transformations such as shuffling temporal order of frames. Then discriminator is encouraged to predict the applied transformation by introducing an auxiliary loss. Subsequently, results prove superiority of the proposed method over baseline methods for providing a useful representation of videos used in human activity recognition performed on datasets such as KTH, UCF101 and Ball-Drop. Ball-Drop dataset is a specifically designed dataset for measuring executive functions in children through physically and cognitively demanding tasks. Using features from proposed method instead of baseline methods caused the top-1 classification accuracy to increase by more then 4%. Moreover, ablation study was performed to investigate the contribution of different transformations on downstream task.

A pipeline for Hand 2-D Keypoint Localization using Unpaired Image to Image Translation

Downloads

Next from PETRA 2021

Structurally Guided Channel Attention Networks: SGCA-Net

Similar lecture

Disentangle, Assemble, and Synthesize: Unsupervised Learning to Disentangle Appearance and Location

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES

A pipeline for Hand 2-D Keypoint Localization using Unpaired Image to Image Translation

.css-70qvj9{display:-webkit-box;display:-webkit-flex;display:-ms-flexbox;display:flex;-webkit-align-items:center;-webkit-box-align:center;-ms-flex-align:center;align-items:center;}Downloads

Next from PETRA 2021

Structurally Guided Channel Attention Networks: SGCA-Net

Similar lecture

Disentangle, Assemble, and Synthesize: Unsupervised Learning to Disentangle Appearance and Location

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES

Downloads