An Amodal Segmentation Pipeline for Critical Infrastructure Asset Imaging
Bibliographic record
Abstract
Computer vision can automatically assess the status of critical infrastructure; however, an unobstructed image of the infrastructure is an often unacknowledged prerequisite for such systems. For roadside-adjacent infrastructure, such as utility poles or fire hydrants, images can be acquired from vehicle-mounted cameras. Large collections of such geotagged images are available from Google Streetview or similar systematic efforts. However, infrastructure in such images is often occluded or otherwise obscured by artifacts. We here improve and extend an existing image retrieval pipeline using generative models for amodal segmentation, such that partially occluded infrastructure can now be automatically detected, regardless of the specific artifact causing the occlusion. In this way, we achieve more robust image retrieval, which will generalize to artifacts arising in various image acquisition systems. Our proposed method leverages Pix2Gestalt to increase obstruction detection from 73.3% to 85.0% in images of utility poles. This leads to a corresponding increase (43.0% to 68.5%) in the infrastructure imaging pipeline’s ability to rectify such occlusions by re-imaging the infrastructure from a different vantage point. Such a robust infrastructure imaging pipeline will be useful to government agencies and utilities seeking to automate critical infrastructure monitoring, maintenance, and disaster recovery efforts.
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 | 0.001 | 0.002 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.003 | 0.001 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.002 | 0.002 |
| Open science | 0.002 | 0.002 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.008 | 0.005 |
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".