Infrared Image Sequences for Dim-Small Aircraft Target Detection and Tracking

Bingwei Hui provides a dataset for dim-small target detection and tracking in infrared images, addressing a lack of measured data in this area. The dataset contains 22 image sequences, 30 trajectories, 16,177 frames, and 16,944 labeled targets. It was created via outfield recording and post-processing, covering scenarios with sky and complex field backgrounds.

Use Cases

• Training object detection models for dim-small targets based on labeled infrared image sequences.
• Developing and benchmarking target tracking algorithms based on the 30 provided trajectories.
• Studying infrared target characteristics under different backgrounds (sky and complex field) as described.
• Researching precision guidance systems using real-world infrared target data.

Strengths

• Contains 16,177 frames of infrared imagery, providing a substantial visual corpus.
• Includes 16,944 labeled target instances with location annotations.
• Covers two distinct acquisition scenarios: sky background and complex field background.

Limitations

• Column-level documentation is absent; field semantics must be inferred after download.
• Row count is unknown, which may limit suitability assessment.
• Last update date is unknown; freshness unverified.

Provenance

Source

Bingwei Hui

Collection Method

Created via outfield recording and post data processing.

Time Range

null

Freshness

Last updated date is unknown.

Geography

null