EECS

Project Daredevil is a technology meant to aid people who are visually impaired to allow them more hands-free independence. The goal is to use cameras to take videos and process the video in real time to detect objects. With the detection of objects, we also need to inform the user how far away detected objects are, and we do this by using depth detection. In order to accomplish this we incorporate dual camera technology, OpenCV, YOLO, and Tensorflow. The results are a working prototype of a device that can detect images and their depth to give feedback to the user.

The motivation behind this project is to eliminate the amount of time that a driver is distracted. This will be done through sound and visual on-board LEDs. Furthermore, the system will monitor the state of a driver and forward statistics to an online site or mobile application. This information is meant to alert concerned parties of the current user’s driving state in real-time

Many travelers struggle to carry luggages, often hampered by holding other belongings such as documents, bags, and etc. Carried away, our autnomous luggage, solves this issue by following the user/owner. This alleviates the stress of carrying multiple objects. The autonomous luggage follows the user through their phone and has sensors to avoid hitting people/objects. 

People do forget stuff. Various objects are put into places like cupboards, bookcases, and refrigerators but never get retrieved because their positions are too far behind the eyesight. Then, things become forgotten and wasted and duplicated items are bought.

This project consists of a smart object tracking system that can be applied to embedded devices to digitalize containers like shelves and refrigerators. By using a hybrid model of traditional edge-detection algorithm and novel neural network, the system can first record the category of any inbound or outbound object, then update its positional information efficiently. After uploading all information to a remote server, user can then use a mobile application to check the storage anytime with Internet connection.

Currently, the system is deployed on a Nvidia Jetson Nano development board with a IMX 219 camera of 8MP and 160 FOV attaches to it. The Jetson Nano is running with Linux operation...

UCI has a dedicated GPS application, known as ZotFinder, that works similar to conventional GPS applications, such as Google Maps. However, one fundamental problem this application contains is the lack of indoor mapping, which could prove problematic when traversing difficult-to-find indoor locations, such as classrooms and offices. Our goal with ZotFinder 2.0 is to solve this aforementioned problem and create an application that can navigate not only outdoor locations, but also indoor classrooms throughout UCI using modern technological trends, namely augmented reality. 

According to figures from the State of California Department of Finance, the State of California is projected to reach a population of 45 million by the 2030s. Meanwhile, whether at home or at work, technology will continue to become a more integral part of everyday life. As a result, loads on energy grids will worsen and the increase in population in the United States’ center of technology will amplify this effect. Especially after switching to time-of-use (TOU) pricing, energy service providers may be forced to charge customers, including residential homes, higher prices for energy use during peak hours due to an increase in energy demand and production. Its impact on the environment would involve the potential rise in carbon emissions depending on the availability of renewable energy sources. For both residential and business consumers, it may be difficult to determine specific areas or devices for which to charge usage patterns...

The robot will be given a set of randomly generated GPS locations. After autonomously traveling to a location, it will orient itself towards its origin point and raise a target for 5 seconds. During this time, the robot will detect if the target is shot during this time. Afterward, it will continue to travel to every other location and perform the same targeting procedure until it arrives back at the origin.

Our project is about Smart Lock that uses facial recognition and EEG signal to unlock the door lock. By applying machine learning and regression techniques, we will be able to process the data making it a database, and therefore people should be able to unlock it although EEG signal is different at seconds for every individual.

With the emergence of the MR (Mixed Reality) concept in the 1990’s, MR has been subject of intense research.  One outcome of this research is the realization that MR environments can be used in the development of games for the purpose of enhancing gameplay experiences.  These approaches, however, often center around the use of AR (Augmented Reality) headsets which convey visual information directly from the virtual environment to the physical.  An alternate method of conveying information is the usage of theatre practices to guide participants in the MR environment through the experience. By utilizing physical props embedded with wearable IoT (Internet-of-Things) devices and vocal guidance such as backleading for subjects to interact with a virtual environment, researchers can develop new methodology for MR gameplay.

One major hurdle of non-visualized MR experiences is successfully conveying information between the virtual and physical environments.  To remedy this problem, game designers and developers...

Teacher's Pet is a tool for automated formative assessment and comprehension analysis. Its design goal is to improve communication, understanding, and education in classroom or corporate training settings with a low-cost and innovative solution leveraging natural language processing (NLP) algorithms, embedded systems, and serverless cloud computing. 

The Handheld Automatic Guitar Tuner is a device that automatically turns the string's tuning peg to the desired frequency. The device will utilize signal processing techniques to filter noise from the string vibration frequency. The information from the device will then be relayed to the users through a mobile application, which provides a user-friendly interface.

As part of the UCI Solar Car team, this project seeks to design a control system for the powertrain of a solar powered vehicle. Running at 96V, the powertrain is composed of a 4 squared meter solar array, a 5kWh lithium ion battery pack, and a 2HP DC brushless motor. The control system that is being designed will enable the driver to shut the vehicle on/off,  apply cruise control, or change the direction of the vehicle's motion. Furthermore, the control system will feature several emergency shutdowns and a telemetry system. The latter will measure and then display important vehicle data to the driver. This will allow the driver to maintain an efficient driving style. 

D.R.I.P.

Python Script that imports OpenCV's open software library to apply facial/eye detection in order to process the video frame and put on articles and accessories onto the user through the mirror. Testing/Development has been done on our team's local machines, but the final presentation is set to be run on our raspberry pi 4. 

We are team MALD and our project is to design a motorized brace to help with joint movement. Our brace will used to help bedridden patients prevent pressure sores from forming due to being immobile for a long period of time. Our aim is to provide comfort for people that can not help themselves.

Project Scarecrow is a smart scarecrow that uses the Google Coral Development Board to perform objection detection without a cloud. See our attatched report for more information!

The Antarctica Ross Ice-Shelf ANtenna Neutrino Array (ARIANNA) is a neutrino detector located in Antarctica.  The neutrino detector works by amplifying weak radio frequency signals generated by neutrino-ice molecule interactions. However, the current amplifier board used by ARIANNA is no longer in production and needs to be redesigned. The goal of our project is the replication and enhancement of the low noise amplifier currently used by the ARIANNA collaboration.

The project is aimed towards making the business class experience more comfortable and satisfactory for the passengers which in turn would be revenue-generating for airlines. Based on research, using technology in passengers’ cabins would improve satisfaction rate of passengers. One technology that can be added to make the cabin systems easier to use is the voice recognition system.This would make interactions with entertainment and seat systems a lot easier. In addition to the fact that it is more convenient, it is useful for passengers with disabilities. If a passenger is unable to type or push buttons to make a request, he/she can do that through the voice recognition system.

Our project goal is to construct a voice recognition device specifically designed for business class passengers to easily interact with their IFE System/respective environment. This device would be able to recognize and translate speech into text, intelligibly process this information and...

The purpose behind this project is to build an autonomous RC car that can do the following: (1)  navigate through lanes, (2) detect objects, and (3) respond to those objects with the appropriate action such as stopping at a red light. 

Students waste time finding study spaces before finding one with adequate space. Currently, there is no efficient way to track real-time occupancy of rooms. 

CrowdVision aims to count the number of people in an image taken by a Raspberry Pi, and makes this data available to students in an easy-to-use web app.

GitHub: https://github.com/jens321/CrowdVision

Humans aren't perfect and neither are irrigation systems. With large areas of land to oversee, farm owners could set their irrigation system to over or under water at certain spots without even realizing. The RSMR was made to help recognize these issues easier and quicker. Inspired by Disney's Wall-E, the RSMR will traverse on its own in hopes to save the world by taking care of what is left of nature. In this case, the RSMR is here to take care of plants and the environment by showing potential areas where water conservation can be improved. Our team's goal is to make helping the planet a little easier. 

Installing permanent external home speakers typically requires you to run wires through internal and external walls. This process requires damaging both internal and external walls leading to costly repairs. There is also the real concern of asbestos exposure when doing this sort of project on older homes which adds an uneccessary danger to external home audio. The Sonido wireless solar-powered speaker aims to eliminate the need for internal-to-external wiring on a house while providing audio entertainment outside the home.

Background:

The Point to Point Self Adjusting Microwave Link is a deployable system that gives companies, hobbyist and the military the ability to get a communication link up with little manual labor. This system must be capable of self-aligning, given an azimuth, to the transmitting site location without the need of having technicians do a manual path alignment. This system is motivated by the idea that while testing missiles, there can be negative results when radio links go down.

Goals & Objectives

Develop a auto-aligning microwave link, aligning to the highest RF peak power to maximize the link’s efficiency. Consisting of a transmit site and receive site to establish an efficient microwave link.

Team Members

David Tiao

      tiaod@uci.edu

Wilfredo Paraiso

      wparaiso@uci.edu

Jeffrey Du

     jeffreld@uci.edu

Advisors

Professor Zak Kassas

     zkassas@uci.edu

Dr. Mahdi Maaref

     mmaaref@uci.edu

Hello We are team Oculus. 

Ultrasound technology is currently being used to visualize the interior structure of the eye for locating abnormalities. However, the major limitation of this approach is that most of the ocular ultrasonography viewing devices can only display two-dimensional scans that provides the physician with limited spatial information, complicating the process of diagnosing the patient. And there are few products on the market that can create a three-dimensional model of the patients’ eyes to diagnose intraocular diseases. There have been documented attempts to develop systems that can produce 3-D models and are suitable for use on the human body. However, various obstacles have slowed down the progression and success of these systems. Since the sequence of the acquired tomographic images is crucial to the formation of the desired 3-D model, the geometry of the body part must be known in order to avoid any distortions, and the...

THEIA is a portable and affordable take on the modern Heads-Up Display. Attachable to any pair of eyewear, THEIA provides any user with a concise display of information right in front of their line of sight. Cyclists need not distract themselves by looking down at an external speedometer when their speed is displayed on the road ahead of them. People concerned with their calorie intake can see the nutritional facts of their food as they look at it. Facts about various items can be displayed as those items appear in the line of sight of the user. THEIA is meant to be compact and portable, able to attach to any eyewear as to not require the fabrication of a special pair of glasses. THEIA also uses affordable and convenient technology as to not discount individuals who wish to have a HUD but cannot afford the current AR glasses on the...

The OpenWheel is an open-source, one-wheeled electric skateboard.

The purpose of the following project is to create a general purpose data acquisition system for use in sensing applications. As a proof of concept, the system is configured to interface with a biological subject through electromyographic surface electrodes. The signals of interest are arm and hand contractions. The overall objective established for the fall was to construct a rudimentary system prototype. The intention was to test amplification of low frequency signals and allow for single and dual channel data acquisition that is transmitted to a user interface via serial connection. The interface serves to display the acquired signals in real-time waveform plots. In order to achieve the quarter goal, a few methods of design and engineering were implemented. SPICE analysis was used to assist in the selection of a low-frequency, small signal amplifier. The rest of the components were selected based on currently available commercial circuits. The control system...

The "Traffic Light Optimizer" is a project designed to better the flow of traffic at intesections through logic synthesized by object detection.

In response to developing countries’ dependence on inefficient international search and rescue teams (ISAR), the GPS Sound Sensor (GPSSS) is a device that can detect the direction of a sound source using time delay of arrival (TDOA) processing. Ultimately, the goal is to send data into an Android App and display the direction of the sound source and the location and orientation of the device. A potential future addon for this device is detecting that the sound source is from a human (rather than an animal), thus decreasing false positives and becoming more reliable [1].

The GPSSS’s main purpose is to be used in search and rescue (SAR) after natural disasters. SAR teams in developing countries do not usually have the manpower or funding to cover wide areas to search for survivors. Non-government organizations such as Red Cross or other ISAR teams often arrive too late to help and save...

This project will revolutionize asset transportation.

The autonomous target scoring drone project description was brought forth by the United States Navy.  The specifications call for a drone that is connected wirelessly to any laptop at some pre-specified base station.  Through some graphical user interface, a user would specify a list of GPS coordinates that would contain physical archery-style targets laid out on the ground.  The drone would then fly autonomously fly to each target and perform image processing on each target.  Each target would have a mark of some kind on it, and the image processing module would produce a score representing how far away the mark is from the center of the target.  All of this information is to be shown on the graphical user interface so the user can see exactly what is happening.

Our group has taken some design liberties with this specification, while still maintaining the core specification of the project.  We...