The iCVL offers various senior projects for teams 2-4 students, either as a semester or year-long project course in Computer Science (marked CS) or as a year-long project in Software Engineering (marked SE). The list below is kept up to date (and currently updated for the fall semester 2018-2019) and always contains projects that are open.
Polygonal puzzle solver (CS,SE)
As mentioned above, (see stable marriage project), our lab has been pushing the abilities to solve visual puzzles to new fronts, including implementations of robotic puzzle solving for what is known as “square puzzles” (puzzles of square pieces). In this project will explore the solution of simple polygonal puzzles both in the computer and by a robotic arm, bringing us closer to real life applications like archeology (where pieces rarely are square) . For details please contact: Prof. Ohad Ben-Shahar.
A high tech fish tank for the study of animal behavior (CS,SE)
Computational Vision could be a wonderful tool for the study of animal behavior. Indeed, instead of allocating human observers to monitor the animals and document their behavior, why not placing a camera and a computer to do so? In this project we will do exactly that to study unique behavioral patterns by gold fish and archer fish. In fact, we will develop a high tech fish tank that monitors the fish to report their psoe (location and direction) within the tank while controlling multiple feeders that reward the fish as soon as they reach certain locations in the tank or accomplish certain tasks. This project is part of a larger research project in collaboration with the Ronen Segev’s lab in the Life Sciences department and will result in the first-ever fully automatic fish tank that trains and observes fish behavior all by itself in order to answer scientific questions at the forefront of neuroscience. For details please contact: Prof. Ohad Ben-Shahar.
An computational generator of geometric visual illusions (CS,SE)
Optimal illusions are a fascinating phenomenon that captures the imagination and often provides insights into the function of our visual system. In this project we would like to develop an end-to-end system that generates topology-disturbing geometric optical illusions of the sort invented by Kokichi Sugihara and popularized in the 2016 best optical illusion contest and shown here. Such a system will allow users to specify the viewer and mirrors position (and we will even attempt to generalize the illusion to more than one mirror!) and what perceptual shapes are desired, and if those shapes prove produce the real 3D shape that one needs to generate in order to obtain the illusions. The system will also convert this shape to a proper representation (i.e., file format) that can be used with the 3D printers in our lab, so the illusions can be constructed in real life.
For details please contact: Prof. Ohad Ben-Shahar.
Hyperspectral vision (CS)
While color vision allows humans and other primates to see the world in amazing detail, light in the visible spectrum carries more information than just “Red, green and blue”, advanced “Hyperspectral” cameras allow us to explore the would around us in greater detail revealing the hidden colors that lie beyond the capabilities of human vision. In this project we will use advanced hyperspectral imaging equipment to observe natural scenes and study their properties. Several projects may be available under this topic. For details please contact: Mr. Boaz Arad or Prof. Ohad Ben-Shahar.
Eye movements in the wild (CS)
Humans execute rapid eye movements between locations well over 100,000 times a day. These movements are an integral part of our visual system, serving in acquiring relevant information, tracking visual targets, and allowing us to operate in our world. Tracking eye-movements and measuring how they change in response to different visual stimuli provide a window into human visual perception. Recent portable eye-tracking technology allows to measure eye movements under natural conditions. Most research based on this technology explores the nature of the visual system when it is bound to a specific and explicit task (e.g., driving, walking or preparing food). But, what could eye-movements tell us about the visual system when it is independent of any specific or explicit task? In order to answer this question, we will measure human eye-movement behavior under free viewing conditions in the outdoors using goggles with eye tracking capacities. By analyzing the measurements, we will interpret the human visual system under natural conditions and seek for ways to incorporate this knowledge into artificial visual systems. For details please contact: Mr. Rotem Mairon or Prof. Ohad Ben-Shahar.
If Waze made ways social, Ize will do so for eyes. In this project we will develop a mobile application where our eyes are shared for the benefit of all. Fun is guaranteed! For details please contact: Prof. Ohad Ben-Shahar.
In the drone area, where copters already accomplish a range of tasks from taking selfies to deliver packages, it is only imagination that limits what we can do with such devices. In this project we will develop a security drone to replace static surveillance camera system. This drone will possesses a certain degree of autonomy in paroling and securing a predefined property while streaming life video and reporting suspicious activities to the operator. For details please contact: Prof. Ohad Ben-Shahar.
Another drone-based project, suitable in particular to the BGU campus, we will attempt develop a system that find cars who park illegally around campus (or a given parking lot). Unlike BGU’s parking warden, who travels around the parking lot with his electric scooter, we will develop a drone system that does so automatically and registers illegally parking cars based on their windshield permit and the characterization of the parking lot. For details please contact: Prof. Ohad Ben-Shahar.
Augmented Reality for architectural design (CS,SE)
Architects and interior designers design draw their plans as 2D sketches. Customers, however, are not able to visualize their house from these drawings and desired 3D simulations of their house. How wonderful could it be if this gap could be bridged directly from the 2D drawing using one’s smartphone. In this project we will implement a simple augmented reality system that observes simple 2D drawings of one floor houses and in real time augments the proper 3D structure over it. Additional features over the basic capacity will be considered along the project. For details please contact: Prof. Ohad Ben-Shahar.
Augmented reality Geo-locator app (SE)
How often does it happen to you that you scan the scenery, observe far urban or rural settlements from a distance but do not know to name them? In this project we will develop a mobile app that solves this problem by endowing the reality observed by the smart device with proper geographical labels while taking into consideration visibility constraints. Additional features over the basic capacity will be considered during the project. For details please contact: Prof. Ohad Ben-Shahar.
Deep learner for arithmetic operations (CS)
Deep learning, a class of machine learning techniques, drives computer science crazy, beating virtually every other method in performance on a variety of tasks. In this project we will try something simple but powerful – could a deep learning network learning arithmetic operations in a certain domain? In this project we will explore this question and develop a system that takes this to a test. Creativity and originality are mandatory! For details please contact: Prof. Ohad Ben-Shahar.
Deep learning for Shape from Shading (CS,SE)
Ill-posed inverse problems in vision (or other domains) are one-to-many problems where the I/O mapping is under-determined. In some very basic sense, the vision problem as a whole is one grand inverse problem. For decades now the computer vision community has been addressing such problems using regularized optimization – a fancy terms to say more constraints are needed to single our certain solutions over others. Could deep learning, the new king in town, do better? In this project we will study some literature and experiment with one of the most basic inverse problems vision, where the shape of objects is to be inferred from their images. For details please contact: Prof. Ohad Ben-Shahar.
Artificial lifeguard (CS,SE)
As we occasional hear in the news, people, especially children, often experience emergencies in pools, and often loose their lives because help is not available on time. In this project we will work towards an artificial life guard that monitors the pool, identifies emergency situations, and calls for help when needed. Despite its applicative nature, this project incorporate significant research work using machine learning methods. For details please contact: Prof. Ohad Ben-Shahar.