A Biologically Inspired Model for the Detection of External and Internal Head Motions
TL;DR: A biologically inspired model is proposed that builds upon the known functional organization of cortical motion processing at low and intermediate stages to decompose the composite motion signal.
Abstract: Non-verbal communication signals are to a large part conveyed by visual motion information of the user's facial components (intrinsic motion) and head (extrinsic motion). An observer perceives the visual flow as a superposition of both types of motions. However, when visual signals are used for training of classifiers for non-articulated communication signals, a decomposition is advantageous. We propose a biologically inspired model that builds upon the known functional organization of cortical motion processing at low and intermediate stages to decompose the composite motion signal. The approach extends previous models to incorporate mechanisms that represent motion gradients and direction sensitivity. The neural models operate on larger spatial scales to capture properties in flow patterns elicited by turning head movements. Center-surround mechanisms build contrast-sensitive cells and detect local facial motion. The model is probed with video samples and outputs occurrences and magnitudes of extrinsic and intrinsic motion patterns.
Summary (2 min read)
- The recent development of computers show a clear trend towards companion properties [4, 14].
- To achieve this, those systems must be able to interpret non-verbal communication patterns that are signalled by the user [2, 5].
- Subsequent classification stages profit from a segregation of these patterns.
- The method is studied on the example of head movements and dynamic facial expressions which both cause optic flow at the observer position.
- The authors model mechanisms of signal processing in early and intermediate stages of visual cortex to provide robust automatic decomposition of extrinsic and intrinsic facial motions.
2 Visual Representations of Head Movements
- The instantaneous motion of a three-dimensional surface that is sensed by a stationary observer can be represented by the linear combination of its translational and rotational motion components , as well as non-rigid motion caused by object deformations.
- The authors aim at spatial processing of the resulting patterns to individually detect the extrinsic and intrinsic components.
- The apparent motion on the positive half circle, where the facial surface is oriented towards the observer, leads to a generic speed pattern.
- This pattern corresponds to the speed gradients as investigated by  and is also depicted in Fig.
- In order to analyze such intrinsic facial motions, the authors reasoned that a centersurround mechanism for the filtering of motion patterns within the facial region will indicate occurrences of intrinsic motions, see Sec. 2.2.
2.1 A Model of Cortical Motion Gradient Detection
- In the following the authors describe the implementation details of their model cells for detecting motion patterns that are characteristic for extrinsic motions corresponding to rotations around the X- or Y -axis, respectively, namely patterns containing speed gradients.
- All presented detectors need a visual motion field u which is transformed into a log-polar representation, the velocity space V.
- This representation allows selecting image locations containing certain motion directions, speeds, or both, which will be fundamental features for the upcoming design of gradient cells.
- First, conjunctive input configurations need to match their tunings for speed and directions, and second, an increase or decrease in speed along an axes corresponding to their directional exists, also known as 3.
- Each cell response incorporates a divise normalisation component in order to keep responses within bounds.
2.2 Model Mechanisms for Motion Contrast Detection
- Local facial motions can be accounted by mechanisms that operate on a smaller scale within the facial projection into the image plane.
- To detect intrinsic motion, the authors propose cells that are sensitive to local changes in speed and direction.
- These motion patterns are produced in the facial plane while the person is talking or during other facial actions.
- The input integration of velocity responses is defined by weighted kernels Ω with different spatial scale dimensions operating on responses of motion and speed selective filters.
- Integration over N directions yields the activation for a direction-insensitive motion contrast cell.
- The authors model was probed with short video sequences containing extrinsic or intrinsic motion.
- The optic flow was then transformed into velocity space representation and presented to proposed model cells.
- The middle section of Fig. 4 shows results for sequences of unconstrained motion, where persons could move the head ad libitum.
- Plots of the activations are also shown in the figure.
- Also, detectors for intrinsic motion show activations that correlate well with eye blink labels.
4 Conclusion and Discussion
- These movements are perceived as composite motion signals by the observer.
- Correct interpretation regarding user dispositions and non-verbal communication patterns from visual signals requires segregated processing of both sources.
- The authors propose networks of cortical motion processing to detect the individual occurrences of intrinsic and extrinsic motion.
- Both proposed detectors work well on facial images and segregate composite facial motion into their extrisinic and intrinsic components.
- In contrast to other approaches their proposed model is independent from highly specialised models, tracking, learning from examples or large optimisation stages to derive the presented results.
Did you find this useful? Give us your feedback
Cites background from "A Biologically Inspired Model for t..."
...Additionally to the analysis of audio signals, many different approaches have been followed on emotion recognition from visual input for example in the form of facial expressions, movement cues  and body gestures ....
Cites methods from "A Biologically Inspired Model for t..."
...A number of techniques have been used for feature extraction, such as facial landmark detection –, optical flow calculation –, appearance modeling , and head pose tracking –....
Cites methods from "A Biologically Inspired Model for t..."
...These results were generated using a restricted set of biologically plausible motion detectors sensitive to motion gradients and local contrasts  read out and combined from a multiscale filter bank....
...4B we finally show the results of a similar approach , where a set of biologically inspired filter combinations was successfully used for the detection of head rotations and eye blinks in real image sequences....
Related Papers (5)
Frequently Asked Questions (2)
Q1. What are the contributions mentioned in the paper "A biologically inspired model for the detection of external and internal head motions" ?
The authors propose a biologically inspired model that builds upon the known functional organization of cortical motion processing at low and intermediate stages to decompose the composite motion signal.
Q2. What are the future works in "A biologically inspired model for the detection of external and internal head motions" ?
Future work will include a validation of the approach for more generic shape-from-motion tasks.