Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Context Adaptive Extended Chain Coding for Semantic Map Compression

Runyu Yang, Junqi Liao, Hyomin Choi, Fabien Racapé, Ivan V. Bajić

TL;DR

This paper studies lossless compression of semantic maps through a novel chain-coding-based framework that explicitly exploits contour topology and shared boundaries between adjacent semantic regions through a novel chain-coding-based framework.

Abstract

Semantic maps are increasingly utilized in areas such as robotics, autonomous systems, and extended reality, motivating the investigation of efficient compression methods that preserve structured semantic information. This paper studies lossless compression of semantic maps through a novel chain-coding-based framework that explicitly exploits contour topology and shared boundaries between adjacent semantic regions. We propose an extended chain code (ECC) to represent long-range contour transitions more compactly, while retaining a legacy three-orthogonal chain code (3OT) as a fallback mode for further efficiency. To efficiently encode sequences of ECC symbols, a context-adaptive entropy coding scheme based on Markov modeling is employed. Furthermore, a skip-coding mechanism is introduced to eliminate redundant representations of shared contours between adjacent semantic regions, supporting both complete and partial skips via run-length signaling. Experimental results demonstrate that the proposed method achieves an average bitrate reduction of 18\% compared with a state-of-the-art benchmark on semantic map datasets. In addition, the proposed encoder and decoder achieve up to 98\% and 50\% runtime reduction, respectively, relative to a modern generic lossless codec. Extended evaluations on occupancy maps further confirm consistent compression gains across the majority of tested scenarios.

Context Adaptive Extended Chain Coding for Semantic Map Compression

TL;DR

This paper studies lossless compression of semantic maps through a novel chain-coding-based framework that explicitly exploits contour topology and shared boundaries between adjacent semantic regions through a novel chain-coding-based framework.

Abstract

Semantic maps are increasingly utilized in areas such as robotics, autonomous systems, and extended reality, motivating the investigation of efficient compression methods that preserve structured semantic information. This paper studies lossless compression of semantic maps through a novel chain-coding-based framework that explicitly exploits contour topology and shared boundaries between adjacent semantic regions. We propose an extended chain code (ECC) to represent long-range contour transitions more compactly, while retaining a legacy three-orthogonal chain code (3OT) as a fallback mode for further efficiency. To efficiently encode sequences of ECC symbols, a context-adaptive entropy coding scheme based on Markov modeling is employed. Furthermore, a skip-coding mechanism is introduced to eliminate redundant representations of shared contours between adjacent semantic regions, supporting both complete and partial skips via run-length signaling. Experimental results demonstrate that the proposed method achieves an average bitrate reduction of 18\% compared with a state-of-the-art benchmark on semantic map datasets. In addition, the proposed encoder and decoder achieve up to 98\% and 50\% runtime reduction, respectively, relative to a modern generic lossless codec. Extended evaluations on occupancy maps further confirm consistent compression gains across the majority of tested scenarios.
Paper Structure (16 sections, 10 figures, 6 tables)

This paper contains 16 sections, 10 figures, 6 tables.

Table of Contents

  1. Introduction
  2. Related Work
  3. Chain Coding Methods
  4. Semantic Map Compression
  5. Proposed Scheme
  6. Blob scanning and registration
  7. Context Adaptive Chain Coding Methods
  8. Skip coding mode
  9. Decoding Process
  10. Experimental Results
  11. Benchmarks
  12. Preliminary performance of chain coding methods
  13. Evaluation on Semantic Maps
  14. Ablation Study
  15. Extended evaluation on Occupancy Maps
  16. ...and 1 more sections

Figures (10)

  • Figure 1: Examples of classical chain code representations for contours: Freeman F4 and F8 chain codes, VCC, and 3OT.
  • Figure 2: System schematic of the overall lossless compression system using the proposed extended chain coding (ECC) method.
  • Figure 3: Scanning directions for (a) boundary blobs and (b) inner blobs, where the circle indicates the shared perimeter between two blobs.
  • Figure 4: Illsutration of the proposed (a) extended chain code (ECC) and (b) Relative ECC (RECC), where the red box highlights a quadrant containing less frequent symbols and the blue box highlights the quadrant to which self-reference symbols are mapped for second-order context modeling.
  • Figure 5: Example of the proposed extended chain coding process for (left) a boundary blob and (right) an inner blob, showing ECC symbol assignment, rotation-based mapping to relative ECC (RECC) symbols, self-reference used for context derivation, and the resulting final chain code sequence.
  • ...and 5 more figures