Systematic Evaluation of Biologically Inspired Motion Detection Models: From LGMD and EMD to Hybrid Spiking Neural Networks
Vanessa Ndiangang, Pengcheng Liu · 2026
Read Systematic Evaluation of Biologically Inspired Motion Detection Models: From LGMD and EMD to Hybrid Spiking Neural Networks by Vanessa Ndiangang, Pengcheng Liu (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-13297146.txt.
Description
Vanessa Ndiangang and Pengcheng Liu benchmark three insect-inspired motion detectors for collision warning in a 2026 evaluation. Insects spot looming objects fast with tiny brains, a trick robots would love to copy. Synthetic test scenes with known answers were used to compare two classic models and a hybrid spiking network.
The hybrid system scored best overall, with perfect precision and faster running than the classic looming detector. The looming model showed the rate sensitivity expected from biology. The directional model correctly stayed quiet for looming stimuli, confirming it answers a different question. The authors flag the jump from synthetic scenes to the real world as the main hurdle ahead.
Catalog record
| CREATOR | Vanessa Ndiangang, Pengcheng Liu |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 60 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |