Thursday, May 21, 2015

Road and Lane Detection: Different Scenarios and Models

Advanced Driver Assistance Systems are an integral part of vehicles today. They can be passive, as in merely alerting the driver in case of emergencies, or actively respond by taking over vehicle controls during emergency scenarios. Such systems are expected to reach full autonomy during the next decade. The two major fields of interests in the problem are: road and lane perception, and obstacle perception. The former involves finding out road and lane markers, to ensure that vehicle position is correct, and to prevent any departures. Obstacle detection is necessary to prevent collisions with other traffic, or real-life artifacts like streetlights, stray animals, pedestrians, etc.

Problem Scope


Road and lane perception include detecting the extent of the road, the number and position of lanes, merging and splitting lanes, over different scenarios like urban, highway or cross-country. While the problem seems trivial given recent advancements in image processing and feature detection algorithms, the problem is complicated by the presence of several challenges, such as:

•    Case diversity: Due a verity of real-world parameters, the system has to be tolerant of a huge diversity of incoming parameters. These include:
  1.     Lane and Road appearance: Color, texture and width of lanes. Road color, width and curvature differences.
  2.     Image clarity: Presence of other vehicle, shadows cast by objects, sudden changes in illumination.
  3.     Visibility conditions: Wet roads, presence of fog or rain, night-time conditions.
•    High reliability demands: In order to be useful and acceptable, the assistance system should achieve very low error rates. A high rate of false positives will lead to driver irritation and rejection, while false negatives will cause system compromise and low reliability.

Modalities Used


The state-of-the-art research and commercial systems are looking at several perception modalities s sensors. A quick view at their operation and pros-cons is presented here:

1.    Vision: Perhaps the most intuitive approach is to use vision based systems, as lane and road markers are already optimized for human vision detection. Use of front-mounted cameras is nearly standard approach in almost all systems, and it can be argued that since most of the signature of lane marks is in the visual domain, no detection system can totally ignore the vision modality. However, it must be stressed that the robustness of the current state-of-the-art processing algorithms is far from satisfactory, and they also lack the adaptive power of a human driver.

2.    LIDAR: The most emerging technology is the use of Light Detection and Ranging sensors, which can produce a 3D structure of the vehicle surrounding, thereby increasing robustness as obstacles are more easily detected in 3D. In addition, LIDARs are active sources- thus they are more illuminance adaptive. The LIDAR sensors are however very expensive.

3.    Stereo-vision: Stereo-vision uses two cameras to obtain the 3D information, which is much cheaper in terms of hardware, but requires significant software overhead. It also has poorer accuracy, and leads to more probability error.

4.    Geographic Information Systems: The use of prior geographic database together with known host-vehicle position can in effect replace the on-board processing requirement and enable worldwide ‘blind’ autonomous driving. However, the system needs very accurate positioning in terms of resolution of the vehicle position, as well as updating the geographic database in real-time with changing traffic dynamics and obstacle positions, either by satellite imagery or GPS measurements. The uncertainty in obtaining and updating highly accurate map information over large terrains has constrained it as a complementary tool to on-board processing.

5.    Vehicle Dynamics: The presence of sensors like Inertial Measurement Units (IMUs) provides insight into the motion parameters of the vehicle such as speed, yaw rate and acceleration. This information is used in the temporal integration module, to relate data across several time-frames.

Generic Solutions


The road and lane detection problem can be broken into the following functional modules. The implementation of said modules uses different approaches across different research and commercially available systems, but the ‘generic system’ presented here is present as the holistic skeleton for them.

1.    Image Cleaning: A pre-filer is applied to the image to remove most of the noise and clutter, arising from obstacles, shadows, over and under exposure, lens flare and vehicle artifacts. If training data is available or data from previous frames is harnessed, a suitable region of interest can be extracted from the image to reduce processing.

2.    Feature Extraction: Based on the required subtask low-level features such as road texture, lane marker color and gradient, etc. are extracted.

3.    Model Fitting: Based on the evidence gathered, a road-lane model is fitted to the data.

4.    Temporal Integration: The model so obtained is reconciled with the model of the previous frames, or the GPS data if available for the region. The new hypothesis is accepted if the difference is explainable based on the vehicle dynamics.

5.    Post Processing: After computation of the model, this step involves translation from image to ground coordinates, and data gathering for use in processing of subsequent frames.

Future Prospects


In concluding remarks, we can stress that road and lane segmentation are fundamental problems of Driver Assistance Systems. The extent of complexity can range from passive Lane Departure Warning systems to fully autonomous ‘blind’ drivers. The next step forward is to extend the scope of current detection techniques into new domains, and to improve its reliability. The first requires a better understanding and development of new road-scene models that can capture multiple lanes, non-linear topographies and other non-idealities successfully. The reliability challenge is harder, especially for closed-loop systems, where even small error rates may propagate. It might become essential to include modalities other than vision, and incorporate machine learning to train algorithms better.



                                                                                                   
                                                                             

Tuesday, May 19, 2015

Surround View System for Vehicles and its Advantages for Drivers



ADAS - Advanced Driving Assistance System is a very popular research area all around the globe and has unbelievable future scope. Within ADAS, the latest developing area and market is of Surround view system or Surround vision or Top view system. These systems are meant to provide a central display of the vehicle to the driver from the perspective of a bird's vision.  Hence, another name given to such systems is "Birds' eye view". A glimpse of Surround vision is shown in the figure below. As the name suggests, surround view system provides the view of immediate surroundings to the drivers. Such views are of great assistance to the drivers in precise operations viz., parking maneuvers, driving in heavy traffic conditions etc.




Any bird eye vision system typically involves 4-6 wide angle fish-eye lens cameras mounted all around the vehicle. The installed/mounted cameras have Field of View up to 180 degrees. Such lenses are preferred so that immediate surrounding is completely visible even after the data loss during the implementation of algorithm on captured frames. 

Two types of camera arrangements are generally seen: 

  • 4 cameras: front, back and one on each side view mirrors.
  • 6 cameras: 1 on all four corners, front and back.
Out of these two, the former is most common because of reasons like lesser complications, initial cost-effectiveness etc.

Advantages to Drivers:
  1. Assistance in parking maneuvers because surrounding vehicles and parking slots are easily visible and driver can solely focus on driving rather than peeping into the mirrors for parking safely.
  2. Eliminates the use of mirrors by providing the complete view of surrounding on a single screen.
  3. Any object or vehicle approaching or running close to the vehicle is visible at once.
  4. Being "top-view", the system is free of perspective distortion. In layman's language, drivers are free of constraints like "Objects in the mirror are closer than they appear".
  5. Works properly even on slopes because of reasonably large field of view.
  6. Driver error is reduced or even eliminated, and efficiency in traffic and transport is enhanced.
  7. High-performance driving can be conducted regardless of the vision, weather and environmental conditions.
  8. Many more vehicles can be accommodated, on regular highways but especially on dedicated lanes
                                                                         
                                                                                                         

Monday, May 18, 2015

ROLE OF EEG IN BRAIN TO COMPUTER INTERFACE

Brain has always been a mystery for us. We have reached moon, Everest and where not, but brain is yet to be understood completely.  We invented machines, robots to make our life simpler, but it would become simpler if we could do all those tasks just by thinking and transmitting signals from one brain to another with the help of signal processing!! That day is not far away, thanks to BCI (Brain Computer interface).

Signal Processing


BCI is direct communication pathway between brain and an external device.  In 1924, Hans Berger was first to discover electric activity in human brain that gave an edge to the signal processing to enter into the biology.  After analyzing the interrelation between EEG’s with brain diseases, a new possibility of research of human brain through EEG opened up.

Some of the advantages EEG Signals has in BCI are that it’s non-invasive, portable and cost effective. One need not cut open the brain. Rhythmic activity in brain is influenced by level of alertness and mental state which is exploited while measuring EEG’s. Since signals are read from the surface, it also makes it prone to noise and results in poor signal resolution, blur and dispersion of the electromagnetic waves created by neurons. Still the cost and the fact that artifacts can be removed, make it top choice for BCI. However, recently using advanced functional Magnetic Resonance Imaging (fMRI) and EEG, control of the flight of virtual helicopter was demonstrated using EEG’s.

BCI is a promising technology for people suffering from paralyses. It can be used to restore mobility in paralyzed limbs. By 2000, researchers had created a thought-translation device for completely paralyzed patients which allowed patients to select characters based on their thoughts. By 2008, researchers from Belgium, Spain and Switzerland created BCI that controlled a motorized wheel chair with high accuracy but it was not perfect.

Neuro gaming is another field where using BCI, a player interacts with the console without using controller. Music and scenery is adjusted according to the mood of player judge by his EEG, heart rate and cognitive state. This allows game play to be more realistic.

Undoubtedly, BCI-EEG is a prominent technology in the signal processing domain and will bring transformation in the field of medicine and our lives.