An Experimental Study on ObjectTracking
Bibliographic record
Abstract
This thesis investigated the robustness of 3D object-tracking algorithms undersnowy weather conditions, focusing particularly on snowy scenarios affecting au-tonomous vehicle perception systems. The principal objective was to evaluateand compare the performance of four tracking methods: Kalman Filter, ExtendedKalman Filter, Particle Filter, and ByteTrack. Each method was assessed using Li-DAR data obtained from the Canadian Adverse Driving Conditions (CADC) dataset,representing harsh winter conditions, and the nuScenes dataset, representing clear,optimal weather conditions. The methodology involved processing sequential frames of LiDAR data, detected3D bounding boxes, and tracking objects through association and state estima-tion. Standard metrics such as HOTA, IDF1, AMOTA, and AMOTP were used tomeasure tracking accuracy and consistency across both datasets. Results indicatedsignificant performance degradation for all algorithms under snowy weather con-ditions compared to clear weather. The Kalman methods suffered from the linearbehaviorand the noise, while the Particle Filter provided a more robust estimationdue to its ability to cope with the uncertainty via its multiple hypotheses. Deep learning-based solution ByteTrack demonstrated better performance, withbetter accuracy and fewer identity switches inchallenging scenarios. It wasfoundthat deep learning based tracking can provide more solid guarantee on point tra-jectoryThe study concluded that deep learning-based tracking methods offer enhancedreliability for autonomous vehicles in challenging environments.
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 | 0.002 | 0.009 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.001 | 0.002 |
| Open science | 0.001 | 0.002 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.007 | 0.002 |
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".