Sect 601 Discuss: Sunday 7:00-8:30 PM on ZOOM only (3/29, 4/5, 4/12, 4/19, 4/26, 5/3, 5/10)
ASYNC videos and lectures notes posted every Wednesday and Friday morning during the spring term.
Canvas LMS: Spring 2024
Email: sbsiewert@csuchico.edu
Student Help: Office Hours, My Schedule
Other times by appointment
CSCI 682 Topics in AI - Sensor Fusion 3 Units
Prerequisite: Classified graduate standing.
Typically Offered: Spring only
Further study of selected advanced topics in artificial intelligence as presented in recently published journals; possible emphasis on research interests and/or projects of faculty in the department. Consult the Graduate Coordinator to determine how many units may be counted toward your major.
Grade Basis: Graduate Graded
Repeatability: You may take this course for a maximum of 3 units
Course Attributes: Graduate Division; Laptop required
Course Description: This course emphasizes a balance of top-down and bottom-up theoretical understanding of sensor networks, sensor system and information fusion methods, and continuous monitoring of systems and operational environments to provide situational awareness. Algorithmics and mathematics required to acquire sensor data from concurrent and redundant sensors, both active and passive are studied. This includes review of current research topics on emergent methods and how to use the methods to support higher level application development for applications like self-driving cars, environmental monitoring, and autonomous systems.
Goals: Students will review research papers, software examples, and case studies to understand fundamental sensor fusion approaches including simple correlation, Bayesian and Dempster-Shafer models, machine learning, and Kalman filtering. The course will use MATLAB and OpenCV for top-down algorithm and programming as well as research papers focused on fundamental methods of applications of them. At the end of the course, all students must either draft a research quality survey paper or demonstrate a prototype software that fuses data from two more sensors to improve detection and monitoring systems.
Textbook: Not required, course is taught primarily from notes.
OpenCV online documentation (access for current OpenCV version used): https://opencv.org/
MATLAB: CSU Chico MathWorks Page, CSU Student Quickstart
REFERENCES:
1. Chang, Ni-Bin, and Kaixu Bai. Multisensor data fusion and machine learning for environmental remote sensing. CRC Press, 2018. Amazon link, Publisher link.
2. Blum, Rick S., and Zheng Liu, eds. Multi-sensor image fusion and its applications. CRC press, 2018. Amazon link, Publisher link.
3. McGrath, Michael E. "Autonomous vehicles: opportunities, strategies, and disruptions." (No Title) (2018). Amazon link, Author link.
4. Hall, David Lee, and Sonya AH McMullen. Mathematical techniques in multisensor data fusion. Artech House, 2004. (ISBN 0-89006-558-6) Amazon link, Author link.
5. MATLAB Sensor Fusion and Tracking Toolbox – Web link, Documentation link
CSCI 612 Past Projects: ACV-2022 Videos
YOLO v8 for CV: Roboflow Training & Documentation
Image file formats: QOI, Theora, MPEG, JPEG, PNG, NETPBM (PPM, PGM, etc.)
CV ML - IDSIA, OpenCV ML Viso.ai best CV tools
Important Course Links: PCL , OpenCV
3D mapping: ElasticFusion, EF paper, ORB SLAM, ORB SLAM2
OpenCV (JetPack 4.6 on Jetson - User's Guide, Quickstart),
Oracle Virtual-Box (optional - not required),
Ubuntu Linux LTS, 20.04/18.04 LTS Download (optional - not required),
Linux UVC Supported Cameras, e.g. Logitech C270 and C615 (required).
MV/ML: Modelplace.AI , MediaPipe, PoseNet Code & Docs, OpenPose Code & Docs, PyTorch, Tensorflow, MATLAB ML, MATLAB DL
Cameras: Linux UVC, Logitech C270 & C615. Advanced: Liquid Lens, FLIR Blackfly, Boson.
NVIDIA Tools: Isaac Sim for ML, Computer Vision SDK, Omniverse, Webinars, GPU Tech Conf
UAVs: Know Before you Fly AVs: F1/10 Autonomous Racing