Corpus ID: 23294708

Collision Selective Visual Neural Network Inspired by LGMD2 Neurons in Juvenile Locusts

  title={Collision Selective Visual Neural Network Inspired by LGMD2 Neurons in Juvenile Locusts},
  author={Qinbing Fu and Cheng Hu and Shigang Yue},
For autonomous robots in dynamic environments mixed with human, it is vital to detect impending collision quickly and robustly. The biological visual systems evolved over millions of years may provide us efficient solutions for collision detection in complex environments. In the cockpit of locusts, two Lobula Giant Movement Detectors, i.e. LGMD1 and LGMD2, have been identified which respond to looming objects rigorously with high firing rates. Compared to LGMD1, LGMD2 matures early in the… Expand
Towards a dynamic vision system: computational modelling of insect motion sensitive neural systems
Novel modelling of the locust and fly visual systems for sensing looming and translating stimuli and the effectiveness and flexibility of the proposed motion sensitive neural systems have been validated by systematic and comparative experiments ranging from off-line synthetic and real-world tests to on-line bio-robotic tests. Expand


Bio-inspired Collision Detector with Enhanced Selectivity for Ground Robotic Vision System
A novel collision selective visual neural network inspired by LGMD2 neurons in the juvenile locusts is proposed, enhancing the collision selectivity in a bio-inspired way, via constructing a computing ef ficient visual sensor, and realizing the revealed specific characteristic sofLGMD2. Expand
Modelling LGMD2 visual neuron system
  • Qinbing Fu, Shigang Yue
  • Computer Science
  • 2015 IEEE 25th International Workshop on Machine Learning for Signal Processing (MLSP)
  • 2015
A novel way to model LGMD2 is proposed, in order to emulate its predicted bio-functions, moreover, to solve some defects of previous LGMD1 computational models. Expand
Collision detection in complex dynamic scenes using an LGMD-based visual neural network with feature enhancement
An LGMD-based neural network is proposed with a new feature enhancement mechanism to enhance the expanded edges of colliding objects via grouped excitation for collision detection with complex backgrounds by filtering out isolated excitation caused by background detail. Expand
Redundant Neural Vision Systems—Competing for Collision Recognition Roles
  • Shigang Yue, F. Rind
  • Computer Science
  • IEEE Transactions on Autonomous Mental Development
  • 2013
This modeling study compared the competence of the LGMD and the DSNs, and investigates the cooperation of the two neural vision systems for collision recognition via artificial evolution, and suggests that theLGMD neural network could be the ideal model to be realized in hardware for collisions recognition. Expand
Modeling disinhibition within a layered structure of the LGMD neuron
A different model is proposed, an Inversed Difference of Gaussians (IDoG) filter, which preserves the different level of brightness in the captured image, enhancing the contrast at the edges, which is expected to increase the performance of the LGMD model. Expand
Computational model of the LGMD neuron for automatic collision detection
  • A. Silva, C. Santos
  • Computer Science
  • 2013 IEEE 3rd Portuguese Meeting in Bioengineering (ENBENG)
  • 2013
A comparative analysis between the new computational model of a locust looming-detecting pathway and the model previously proposed, which proved the improvement provided by the pixel remapping in the model performance. Expand
A bio-inspired visual collision detection mechanism for cars: Combining insect inspired neurons to create a robust system
A modified model of the lobula giant movement detector of locusts shows how the neurons pre-synaptic to the LGMD show a remarkable ability to filter images, and only colliding and translating stimuli produce excitation in the neuron. Expand
A Collision Detection System for a Mobile Robot Inspired by the Locust Visual System
  • Shigang Yue, F. Rind
  • Engineering, Computer Science
  • Proceedings of the 2005 IEEE International Conference on Robotics and Automation
  • 2005
A new mechanism to enhance the feature of colliding objects before the excitations are gathered by LGMD cell is proposed, which favours grouped excitation but tends to ignore isolated excitation with selective passing coefficients. Expand
A Synthetic Vision System Using Directionally Selective Motion Detectors to Recognize Collision
This study suggests that whole-field direction-selective neurons, with selectivity based on asymmetric lateral inhibition, can be organized into a synthetic vision system, which can be adapted to play an important role in collision detection in complex dynamic scenes. Expand
Looming detection by identified visual interneurons during larval development of the locust Locusta migratoria
Electron microscopy demonstrates that the anatomical substrate for the selective response to approaching stimuli is present in all larval instars: small neuronal processes carrying information from the eye make synapses both onto LGMD dendrites and with each other, providing pathways for lateral inhibition that shape selectivity for approaching objects. Expand