A5038288003- Video Surveillance and Tracking Methods
- UAV Applications and Optimization
- Infrared Target Detection Methodologies
- Biomimetic flight and propulsion mechanisms
- Visual Attention and Saliency Detection
- Aerospace Engineering and Energy Systems
- Advanced Image and Video Retrieval Techniques
- Diverse Topics in Contemporary Research
- Medical Imaging and Analysis
- Connexins and lens biology
- Smart Systems and Machine Learning
- Robotics and Sensor-Based Localization
- Physiological and biochemical adaptations
- Wildlife Ecology and Conservation
- Endometrial and Cervical Cancer Treatments
- Urinary Bladder and Prostate Research
- Primate Behavior and Ecology
- Olfactory and Sensory Function Studies
- Robotic Locomotion and Control
- Prostate Cancer Diagnosis and Treatment
- Fire Detection and Safety Systems
University of Alberta
2020-2021
University of Tehran
2018
Developing analytical models of efficient locomotion in biology is one the most interesting goals bio- inspired robotics. This paper presents a mathematical framework order to model energy types flying animals; i.e., thermal soaring. Unlike legged locomotion, flying, modeling environmental effects on animals' behaviors very important. In doing so, we develop our by assuming thermals as bubbles rising air. According pieces real evidence, this kind more compatible with nature Moreover, present...
Albatross has an energy efficient flying pattern (dynamic soaring) among seabirds. This interesting point encourages us to exploit its natural dynamics so as control the robots on and robust gaits. In doing so, we study albatross dynamic soaring from analytical biological perspectives realize that generate instead of trajectory control, mechanical should be regulated. Accordingly, objective is set regulation, bank angle lift coefficient are computed satisfy this objective. The presented...
MRI is a powerful imaging technique for examining the anatomy of female reproductive system. However, due to cost-related concerns, ease access, acquisition time, and necessity expert reviewers MR images, ultrasound primary modality choice. To mitigate some these we developed an AI-driven tool comprising seven neural networks that segments regions interest whole uterus, uterine zones, ovaries, further identifies common benign gynecological conditions. We evaluated our package on large...
AI-assisted prostate whole-gland and zonal volume quantification enable quantitative reproducibility enhance read-time efficiency. Our AI-segmentation solution enhanced measurement accuracy by 23.59%, compared with traditional estimates. Zonal enabled us to generate population normative aging-curves we used a shallow classifier identify patients BPH. findings show the transitional zone grows 2.05 ml 3.58 per decade for entire BPH, respectively, while peripheral 0.70 decade. Further, zones...
Motivation: To quantify female reproductive anatomy in MR imaging. Goal(s): develop an AI-based solution to segment the regions of interest (RoIs) for uterine zone, ovaries, pelvic fluid, and detect benign conditions. Approach: A deep learning based method is applied on a large representative population 9334 sagittal T2-weighted pelvis scans extract normative menstrual cycle- aging-curves various RoIs. Results: Our proposed curves define standard cycle aging trends. RoI segmentation,...
We consider the problem of tracking an unknown small target from aerial videos medium to high altitudes. This is a challenging problem, which even more pronounced in unavoidable scenarios drastic camera motion and density. To address this we introduce context-aware IoU-guided tracker (COMET) that exploits multitask two-stream network offline reference proposal generation strategy. The proposed fully target-related information by multi-scale feature learning attention modules. strategy...
A strong visual object tracker nowadays relies on its well-crafted modules, which typically consist of manually-designed network architectures to deliver high-quality tracking results. Not surprisingly, the manual design process becomes a particularly challenging barrier, as it demands sufficient prior experience, enormous effort, intuition, and perhaps some good luck. Meanwhile, neural architecture search has gaining grounds in practical applications promising method tackling issue...
In nature, the collective behavior of animals, such as flying birds is dominated by interactions between individuals same species. However, study among bird species a complex process that humans cannot perform using conventional visual observational techniques focal sampling in nature. For social animals birds, mechanism group formation can help ecologists understand relationship cues and their characteristics over time (e.g., pose shape). But, recovering varying shapes highly challenging...