An Efficient Lidar-Based Algorithm for Autonomous Vehicle's Visual Detection
Bibliographic record
Abstract
The real-time and accurate three-dimensional object detection is one of the core tasks in the perception of autonomous driving environments. In recent years, the development of deep learning technology and lidar technology has led to significant advancements in the application of three-dimensional object detection algorithms in large-scale general scenarios. However, existing lidar-based three-dimensional object detection algorithms still face challenges in complex traffic scenarios, and the difficulty lies in balancing the accuracy and inference speed of the algorithms. In this regard, the voxel-based single-stage three-dimensional object detection algorithm SECOND is used as the baseline algorithm and an efficient single-stage vehicle detection algorithm framework tailored for complex autonomous driving scenarios is proposed. Firstly, a residual structure is introduced and the feature channel number is reconstructed in the three-dimensional feature extraction backbone, which effectively reduce the loss of spatial geometric features in the point cloud during the feature extraction process and make the model training more stable. Secondly, the multi-scale feature fusion technology and a spatial feature attention mechanism are introduced and a more efficient two-dimensional feature fusion backbone is designed, which facilitates the learning of the model for vehicle size and orientation. The proposed algorithm is trained and validated on the open-source dataset ONCE. Compared to the baseline algorithm, the average detection accuracy for vehicles is improved by 5.64%, while maintaining an inference speed of 20 frames per second (FPS). This significantly enhances the algorithm's perception performance for vehicles in complex traffic scenarios.
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 distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
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 teacher head, 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".