Kasim Terzić
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
Kasim Terzić has a total of 33 co-authors. Here are the top co-authors by number of shared publications:
- Joao M. F. Rodrigues
Universidade do Algarve
9 shared publications J. M. H. du Buf
University of the Algarve
7 shared publications- Johannes M. H. du Buf
University of the Algarve
6 shared publications - Halid Abdulrahim Kadi
University of St Andrews University of St Andrews
3 shared publications Bernd Neumann
University of Hamburg
2 shared publicationsDavid Lobato
University of the Algarve
2 shared publications
Latest Publications
- Open Access
Agent-Arena: A General Framework for Evaluating Control Algorithms
Robotic research is inherently challenging, requiring expertise in diverse environments and control algorithms. Adapting algorithms to new environments often poses significant difficulties, compounded by the need for extensive hyper-parameter tuning in data-driven methods. To address these challenges, we present Agent-Arena, a Python framework designed to streamline the integration, replication, development, and testing of decision-making policies across a wide range of benchmark environments. Unlike existing frameworks, Agent-Arena is uniquely generalised to support all types of control algorithms and is adaptable to both simulation and real-robot scenarios. Please see our GitHub repository https://github.com/halid1020/agent-arena-v0.
Open AccessAgent-Arena: A General Framework for Evaluating Control Algorithms
Robotic research is inherently challenging, requiring expertise in diverse environments and control algorithms. Adapting algorithms to new environments often poses significant difficulties, compounded by the need for extensive hyper-parameter tuning in data-driven methods. To address these challenges, we present Agent-Arena, a Python framework designed to streamline the integration, replication, development, and testing of decision-making policies across a wide range of benchmark environments. Unlike existing frameworks, Agent-Arena is uniquely generalised to support all types of control algorithms and is adaptable to both simulation and real-robot scenarios. Please see our GitHub repository https://github.com/halid1020/agent-arena-v0.
- Open Access
- 11 January 2024
- Published by Oxford University Press (OUP) in Biology Methods and Protocols
- Vol. 9 (1) , bpae056
Automatic detection of fish scale circuli using deep learning
Teleost fish scales form distinct growth rings deposited in proportion to somatic growth in length, and are routinely used in fish ageing and growth analyses. Extraction of incremental growth data from scales is labour intensive. We present a fully automated method to retrieve this data from fish scale images using Convolutional Neural Networks (CNNs). Our pipeline of two CNNs automatically detects the centre of the scale and individual growth rings (circuli) along multiple radial transect emanating from the centre. The focus detector was trained on 725 scale images and achieved an average precision of 99%; the circuli detector was trained on 40 678 circuli annotations and achieved an average precision of 95.1%. Circuli detections were made with less confidence in the freshwater zone of the scale image where the growth bands are most narrowly spaced. However, the performance of the circuli detector was similar to that of another human labeller, highlighting the inherent ambiguity of the labelling process. The system predicts the location of scale growth rings rapidly and with high accuracy, enabling the calculation of spacings and thereby growth inferences from salmon scales. The success of our method suggests its potential for expansion to other species.
- 11 January 2024
- Published by Oxford University Press (OUP) in Biology Methods and Protocols
- Vol. 9 (1) , bpae056
Open AccessAutomatic detection of fish scale circuli using deep learning
Teleost fish scales form distinct growth rings deposited in proportion to somatic growth in length, and are routinely used in fish ageing and growth analyses. Extraction of incremental growth data from scales is labour intensive. We present a fully automated method to retrieve this data from fish scale images using Convolutional Neural Networks (CNNs). Our pipeline of two CNNs automatically detects the centre of the scale and individual growth rings (circuli) along multiple radial transect emanating from the centre. The focus detector was trained on 725 scale images and achieved an average precision of 99%; the circuli detector was trained on 40 678 circuli annotations and achieved an average precision of 95.1%. Circuli detections were made with less confidence in the freshwater zone of the scale image where the growth bands are most narrowly spaced. However, the performance of the circuli detector was similar to that of another human labeller, highlighting the inherent ambiguity of the labelling process. The system predicts the location of scale growth rings rapidly and with high accuracy, enabling the calculation of spacings and thereby growth inferences from salmon scales. The success of our method suggests its potential for expansion to other species.
- Open Access
Data-Driven Robotic Manipulation of Cloth-like Deformable Objects: The Present, Challenges and Future Prospects
Manipulating cloth-like deformable objects (CDOs) is a long-standing problem in the robotics community. CDOs are flexible (non-rigid) objects that do not show a detectable level of compression strength while two points on the article are pushed towards each other and include objects such as ropes (1D), fabrics (2D) and bags (3D). In general, CDOs’ many degrees of freedom (DoF) introduce severe self-occlusion and complex state–action dynamics as significant obstacles to perception and manipulation systems. These challenges exacerbate existing issues of modern robotic control methods such as imitation learning (IL) and reinforcement learning (RL). This review focuses on the application details of data-driven control methods on four major task families in this domain: cloth shaping, knot tying/untying, dressing and bag manipulation. Furthermore, we identify specific inductive biases in these four domains that present challenges for more general IL and RL algorithms.
Open AccessData-Driven Robotic Manipulation of Cloth-like Deformable Objects: The Present, Challenges and Future Prospects
Manipulating cloth-like deformable objects (CDOs) is a long-standing problem in the robotics community. CDOs are flexible (non-rigid) objects that do not show a detectable level of compression strength while two points on the article are pushed towards each other and include objects such as ropes (1D), fabrics (2D) and bags (3D). In general, CDOs’ many degrees of freedom (DoF) introduce severe self-occlusion and complex state–action dynamics as significant obstacles to perception and manipulation systems. These challenges exacerbate existing issues of modern robotic control methods such as imitation learning (IL) and reinforcement learning (RL). This review focuses on the application details of data-driven control methods on four major task families in this domain: cloth shaping, knot tying/untying, dressing and bag manipulation. Furthermore, we identify specific inductive biases in these four domains that present challenges for more general IL and RL algorithms.
- Open Access
- 16 December 2022
- Published by MDPI AG in Preprints.org
Data-Driven Robotic Manipulation of Cloth-like Deformable Objects: Present, Challenges, and Future Prospects
Manipulating cloth-like deformable objects (CDOs) is a long-standing problem in the robotics community. CDOs are flexible (non-rigid) objects that do not show a detectable level of com- pression strength while two points on the article are pushed towards each otherand include objects such as ropes (1D), fabrics (2D) and bags (3D). In general, CDOs’ many degrees of freedom (DoF) introduce severe self-occlusion and complex state-action dynamics as significant obstacles for perception and manipulation systems. These challenges exacerbate existing issues of modern robotic control methods such as imitation learning (IL) and reinforcement learning (RL). This review focuses on the application details of data-driven control methods on four major task families in this domain: cloth-shaping, rope manipulation, dressing and bag manip- ulation. Furthermore, we identify specific inductive biases in these four domains that present challenges for more general IL and RL algorithms, and summarise the future direction for the development of the field.
- 16 December 2022
- Published by MDPI AG in Preprints.org
Open AccessData-Driven Robotic Manipulation of Cloth-like Deformable Objects: Present, Challenges, and Future Prospects
Manipulating cloth-like deformable objects (CDOs) is a long-standing problem in the robotics community. CDOs are flexible (non-rigid) objects that do not show a detectable level of com- pression strength while two points on the article are pushed towards each otherand include objects such as ropes (1D), fabrics (2D) and bags (3D). In general, CDOs’ many degrees of freedom (DoF) introduce severe self-occlusion and complex state-action dynamics as significant obstacles for perception and manipulation systems. These challenges exacerbate existing issues of modern robotic control methods such as imitation learning (IL) and reinforcement learning (RL). This review focuses on the application details of data-driven control methods on four major task families in this domain: cloth-shaping, rope manipulation, dressing and bag manip- ulation. Furthermore, we identify specific inductive biases in these four domains that present challenges for more general IL and RL algorithms, and summarise the future direction for the development of the field.
- 1 November 2017
- Published by Elsevier in Image and Vision Computing
- Vol. 67, 43-51
Texture features for object salience
- 1 November 2017
- Published by Elsevier in Image and Vision Computing
- Vol. 67, 43-51
Texture features for object salience
- 16 May 2017
- Published by Springer Nature
- p. 456-467
Interpretable Feature Maps for Robot Attention
- Open Access
- 3 November 2015
- Published by Springer Nature
- p. 331-342
A Parametric Spectral Model for Texture-Based Salience
- 3 November 2015
- Published by Springer Nature
- p. 331-342
Open AccessA Parametric Spectral Model for Texture-Based Salience
- 18 July 2015
- Published by Springer Nature
- p. 505-517
Biologically Inspired Vision for Human-Robot Interaction
- 18 July 2015
- Published by Springer Nature
- p. 505-517
Biologically Inspired Vision for Human-Robot Interaction
- 1 February 2015
- Published by Elsevier in Neurocomputing
- Vol. 150, 227-237
BIMP: A real-time biological model of multi-scale keypoint detection in V1
- 1 February 2015
- Published by Elsevier in Neurocomputing
- Vol. 150, 227-237
BIMP: A real-time biological model of multi-scale keypoint detection in V1
- 10 October 2014
- Published by Springer Nature
- p. 469-477
Biologically Inspired Vision for Indoor Robot Navigation
- 10 October 2014
- Published by Springer Nature
- p. 469-477
Biologically Inspired Vision for Indoor Robot Navigation