Deep learning‐based real‐time fine‐grained pedestrian recognition using stream processing
Bibliographic record
Abstract
Real‐time recognition of pedestrian details can be very important in emergency situations for security reasons, such as traffic accidents identification from traffic video. However, this is challenging due to the needed accuracy of video data mining, and also the performance for real‐time video processing. Here, the authors propose a solution for fine‐grained pedestrian recognition in monitoring scenarios using deep learning and stream processing cloud computing, which is called DRPRS (deep learning‐based real‐time fine‐grained pedestrian recognition using stream processing). The authors design an improved convolutional neural network (CNN) network called fine‐CNN, which is a nine‐layer neural network for detailed pedestrian recognition. In DRPRS, a pedestrian in a surveillance video is segmented and fine‐grainedly recognised using improved single‐shot detector and several fine‐CNNs. DRPRS is supported by parallel mechanisms provided by Apache Storm stream processing framework. In addition, in order to further improve the recognition performance, a GPU‐based scheduling algorithm is proposed to make full use of GPU resources in a cluster. The whole recognition process is deployed on a big video data processing platform to meet real‐time requirements. DRPRS is extensively evaluated in terms of accuracy, fault tolerance, and performance, which show that the proposed approach is efficient.
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 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.000 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 0.001 |
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".