End-to-End Multiview Gesture Recognition for Autonomous Car Parking System
Bibliographic record
Abstract
The use of hand gestures can be the most intuitive human-machine interaction medium. \nThe early approaches for hand gesture recognition used device-based methods. These \nmethods use mechanical or optical sensors attached to a glove or markers, which hinders \nthe natural human-machine communication. On the other hand, vision-based methods are \nnot restrictive and allow for a more spontaneous communication without the need of an \nintermediary between human and machine. Therefore, vision gesture recognition has been \na popular area of research for the past thirty years. \nHand gesture recognition finds its application in many areas, particularly the automotive \nindustry where advanced automotive human-machine interface (HMI) designers are \nusing gesture recognition to improve driver and vehicle safety. However, technology advances \ngo beyond active/passive safety and into convenience and comfort. In this context, \none of America’s big three automakers has partnered with the Centre of Pattern Analysis \nand Machine Intelligence (CPAMI) at the University of Waterloo to investigate expanding \ntheir product segment through machine learning to provide an increased driver convenience \nand comfort with the particular application of hand gesture recognition for autonomous \ncar parking. \nIn this thesis, we leverage the state-of-the-art deep learning and optimization techniques \nto develop a vision-based multiview dynamic hand gesture recognizer for self-parking system. \nWe propose a 3DCNN gesture model architecture that we train on a publicly available \nhand gesture database. We apply transfer learning methods to fine-tune the pre-trained \ngesture model on a custom-made data, which significantly improved the proposed system \nperformance in real world environment. We adapt the architecture of the end-to-end solution \nto expand the state of the art video classifier from a single image as input (fed by \nmonocular camera) to a multiview 360 feed, offered by a six cameras module. Finally, we \noptimize the proposed solution to work on a limited resources embedded platform (Nvidia \nJetson TX2) that is used by automakers for vehicle-based features, without sacrificing the \naccuracy robustness and real time functionality of the system.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.007 | 0.003 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".