Philip Abbet
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Philip Abbet has a total of 9 co-authors. Here are the top co-authors by number of shared publications:
Huang Wei
Intelligent Automotive Solution BU, Huawei Technologies Company Ltd., Shanghai, China
1 shared publication- Ketan Kotwal
Idiap Research Institute, 1920 Martigny, Switzerland
1 shared publication - Sushil Bhattacharjee
Biometrics Security and Privacy Group, Idiap Research Institute, Martigny, Switzerland
1 shared publication - Sylvain Calinon
Idiap Research Institute
1 shared publication - Sébastien Marcel
IDIAP Research Institute, Martigny, Switzerland
1 shared publication - Tobias Löw
IDIAP Research Institute, Martigny, Switzerland
1 shared publication
Latest Publications
- 23 August 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics & Automation Magazine
- Vol. 32 (3) , 184-194
GAFRO: Geometric Algebra for Robotics [Tutorial]
Geometry is a fundamental part of robotics, and there have been various frameworks of representation over the years. Recently, geometric algebra (GA) has gained attention for its property of unifying many of those previous ideas into one algebra. While there are already efficient open source implementations of GA available, none of them is targeted at robotics applications. We want to address this shortcoming with our library Geometric Algebra for Robotics (GAFRO). This article presents an overview of the implementation details as well as a tutorial on GAFRO, an efficient C++ library targeting robotics applications using GA. The library focuses on using conformal GA (CGA). Hence, various geometric primitives are available for computation as well as rigid body transformations. The modeling of robotic systems is also an important aspect of the library. It implements various algorithms for calculating the kinematics and dynamics of such systems as well as objectives for optimization problems (see Figure 1). The software stack is completed by Python bindings in pygafro and a Robotic Operating System (ROS) interface in gafro_ros.
- 23 August 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics & Automation Magazine
- Vol. 32 (3) , 184-194
GAFRO: Geometric Algebra for Robotics [Tutorial]
Geometry is a fundamental part of robotics, and there have been various frameworks of representation over the years. Recently, geometric algebra (GA) has gained attention for its property of unifying many of those previous ideas into one algebra. While there are already efficient open source implementations of GA available, none of them is targeted at robotics applications. We want to address this shortcoming with our library Geometric Algebra for Robotics (GAFRO). This article presents an overview of the implementation details as well as a tutorial on GAFRO, an efficient C++ library targeting robotics applications using GA. The library focuses on using conformal GA (CGA). Hence, various geometric primitives are available for computation as well as rigid body transformations. The modeling of robotic systems is also an important aspect of the library. It implements various algorithms for calculating the kinematics and dynamics of such systems as well as objectives for optimization problems (see Figure 1). The software stack is completed by Python bindings in pygafro and a Robotic Operating System (ROS) interface in gafro_ros.
- 21 January 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Biometrics, Behavior, and Identity Science
- Vol. 4 (1) , 135-147
Domain-Specific Adaptation of CNN for Detecting Face Presentation Attacks in NIR
For the automotive industry moving towards personalized applications and experiences, the identification of the person inside vehicle is necessary; and it must be carried out in a secure manner. In this paper, we propose a unique face presentation attack detection (PAD) system for operation inside a passenger vehicle. A typical in-vehicular face PAD system is required to function with several constraints such as bounded sensing (imaging) capabilities, limited computing resources on embedded devices, real-time inference, and essentially, very high accuracy. In this work, we develop a face PAD system for automotive domain, relying on a single NIR camera, to continually verify whether the driver’s face is bona-fide or not. Our work has two main contributions: first, a lightweight face PAD framework has been developed using a 9-layer convolutional neural network (CNN). With its compact size and limited set of operators, it can be deployed in a resource constrained embedded device to achieve a near real-time inference. To alleviate the problem of limited training data (face PAD in NIR) for a given system, we develop an efficient mechanism to obtain this CNN through the combination of adaptation of domain-specific layers and task-specific fine-tuning of a base CNN. As the second contribution, we collect a large face PAD dataset with 5800+ videos, acquired in NIR (940 nm ) illumination, for in-vehicular use-cases. This dataset, named VFPAD, captures several real-world variations in terms of environmental settings, illumination, subject’s pose, and appearances. Based on the VFPAD dataset, we demonstrate that the proposed face PAD method achieves very high performance (overall accuracy $\approx 98.0$ %), and also outperforms several baseline face PAD methods. The dataset will be shared with the wider scientific community for research purposes.
- 21 January 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Biometrics, Behavior, and Identity Science
- Vol. 4 (1) , 135-147
Domain-Specific Adaptation of CNN for Detecting Face Presentation Attacks in NIR
For the automotive industry moving towards personalized applications and experiences, the identification of the person inside vehicle is necessary; and it must be carried out in a secure manner. In this paper, we propose a unique face presentation attack detection (PAD) system for operation inside a passenger vehicle. A typical in-vehicular face PAD system is required to function with several constraints such as bounded sensing (imaging) capabilities, limited computing resources on embedded devices, real-time inference, and essentially, very high accuracy. In this work, we develop a face PAD system for automotive domain, relying on a single NIR camera, to continually verify whether the driver’s face is bona-fide or not. Our work has two main contributions: first, a lightweight face PAD framework has been developed using a 9-layer convolutional neural network (CNN). With its compact size and limited set of operators, it can be deployed in a resource constrained embedded device to achieve a near real-time inference. To alleviate the problem of limited training data (face PAD in NIR) for a given system, we develop an efficient mechanism to obtain this CNN through the combination of adaptation of domain-specific layers and task-specific fine-tuning of a base CNN. As the second contribution, we collect a large face PAD dataset with 5800+ videos, acquired in NIR (940 nm ) illumination, for in-vehicular use-cases. This dataset, named VFPAD, captures several real-world variations in terms of environmental settings, illumination, subject’s pose, and appearances. Based on the VFPAD dataset, we demonstrate that the proposed face PAD method achieves very high performance (overall accuracy $\approx 98.0$ %), and also outperforms several baseline face PAD methods. The dataset will be shared with the wider scientific community for research purposes.