Development of Smart Gadgets for Intelligent Transportation Systems for Human Safety &

Accurate Vehicular NavigationSatwik Patnaik, B.E. (EnTC), P.R.E.C. Loni & Pranav Parchure, T.E. (EtRX), P.R.E.C Loni

ABSTRACT

This paper provides a review of earlier work and throws some light to some of the proposed developments for the Intelligent Transport System (ITS) for motorcycles and cars. Related issues of the existing systems are also discussed with some existing or emerging ITS technologies. Intelligent Transport Systems (ITS) have a significant potential to enhance traffic & vehicular safety. In the following paper we have proposed, our idea of a helmet/seat belt based safe driving system. We are devising the proposal of a system such that, if the seat belt is not worn properly by the driver, the vehicle in question would not star. We are also proposing the implementation of sending an alert SMS to the family members in case of an accident.

Vehicle Location using GPS has been redefined so that the family members can get to know the location of the vehicle on their Mobile handsets. An algorithm is also proposed which will help to lessen the large number of head-on collisions on busy intersection roads. The present day technology uses the principle of line of sight for collision detection. Hence, it is inefficient for the intersection cases. The feature of Driver Drowsiness system is also discussed which is very interesting to the research engineers involved in ITS. An algorithm has also been proposed with regards to Driver drowsiness system with the help of Digital Image Processing.

There are several ITS technologies like advanced driver assistance system, intelligent speed adaptation, collision warning and avoidance system, etc. However, there is a greater need for the development of standards for design of ITS technologies for motorcycles, as there are for the design of ITS technologies for other vehicles.

Keywords: Intelligent Transport System, GPS, Bluetooth Modem, Digital Image Processing, Neuro-genetic algorithm, Driver Drowsiness.

INTRODUCTION

Intelligent Transportation Systems (ITS) are state-of-the-art approaches based on information, communication and satellite technologies in mitigating traffic congestion, enhancing safety, and improving quality of environment. The term ITS refers to integrated applications, employing combinations of information, communications, computing, sensor and control technologies, which

aim to improve transport safety and mobility and reduce vehicle emissions. Many such technologies have been developed to enhance vehicle safety: to prevent crashes, reduce trauma during a crash or to reduce trauma following a crash. ITS technologies may provide vehicles with different types and levels of “intelligence” to complement the driver. Information systems expand the driver’s knowledge of routes and locations. Warning systems, such as collision avoidance technologies, enhance the driver’s ability to sense the surrounding environment. Now-a-days, the focus of road safety has shifted from collision protection to prevention. Many new accident avoidance techniques have been proposed, ranging from lane detection mechanisms, traffic analysis vision systems, vehicular networks, and tiredness estimation systems. Several intelligent Transportation Systems (ITS) exist to help control the flow of traffic, coordinate signal timing to reduce conflict in intersections, pass important traffic information along to drivers, warn travelers of inclement weather conditions, reduce congestion along toll roads with electronic fare collection. ITS can also be used to gather data and report it to emergency response teams so that response times are reduced.

CAUSES OF HIGHWAY ACCIDENTS AND FATALITIES

The causes of vehicle accidents fall into three main categories: human factors, road and environmental conditions, and vehicle failure or malfunction. But rarely is any accident the result of a single, easily determined cause. In many cases, circumstances leading to a crash involve factors from more than one of the categories. For example, an accident involving a young driver whose brakes aren’t functioning properly driving on icy pavement has several contributing factors, even though only one may be named in the accident report. Reports claims that human factors, which include speeding, violating traffic laws, inattention, age, effects of alcohol and drugs, and decision errors, most often contribute to accidents. Roadway environment, such as roadside hazards, poor road design, pavement conditions and

weather, closely follow human factors, with vehicle factors being the least common contributor to crashes. In order to determine the most effective approaches to reduce highway deaths, injuries, and related costs to acceptable levels, it is necessary to have an accurate and complete picture of the causes and circumstances of traffic accidents. A brief analysis of the NCRB report points to Andhra Pradesh having the highest share of deaths due to road accidents (12%) followed by Maharashtra and Uttar Pradesh (11% each). Almost one-third of all crashes are rear-end collisions.

DEVELOPMENTS

ADVANCED DRIVER ASSISTANCE SYSTEMS

Advanced driver assistance systems (ADAS) are one of the emerging automotive markets, driven by a wide public and industrial interest in improved safety and comfort. Applications like lane departure warning, automatic cruise control, parking aids or night vision have already been introduced. One of the key issues in bringing advanced driver assistance systems (ADAS) like lane-keeping, lane-changing or collision avoidance systems into the market is the design of an appropriate interaction between driver and driver assistance systems. Traditional vehicle collision warning and avoidance systems do not perform well in the perpendicular path intersection case. One major reason is that, the threat detection systems use line-of-sight. It is because the intersection collision problem is more complicated than rear-end crash and the limitations of the radar technology, the most widely used object sensing method in vehicle collision avoidance systems. Most radar systems require line-of-sight for object detection. Yet in most intersection crash cases, the principle other vehicle (POV) is hidden from the line of sight of the subject vehicle (SV) until the last second before the collision. This renders ineffective most collision warning/avoidance systems that require line-of-sight for threat detection. Recently we have designed and developed a system capable of intersection collision warning using a new approach. The system is based on vehicle-to-vehicle communication using ad hoc mobile networks. Threat detections are achieved by vehicles cooperatively sharing critical information for collision anticipation,i.e., location, velocity, acceleration, etc. By sharing the information between peers, each vehicle is able to predict potential hazards. Although this system doesn’t require a support infrastructure, the ultimate value of this kind of peer-to-peer cooperative system depends on the percentage of vehicles on the road using it. The more vehicles using it, the more valuable it is.

ALGORITHM

HUMAN FACTORS CONSIDERATION

Human factors play an important part in the collision warning system design. As the purpose of the warning is to alert the driver when he/she is unaware of, or not responding to a potential collision, a collision warning system should be aware of not only the external collision potential, but also what the driver has and has not done regarding the collision possibility. If the driver has already taken an appropriate action right before a warning is issued, the warning shall be discarded.

Specifications

(1) At most one warning is given at one intersection.

(2) No warning if there is no route contention.

(3) No warning if the driver has already taken appropriate action.

(4) No warning if the time-to-collision (TTC) is much greater than time-to-avoidance (TTA).

Algorithm

1. Listen for relevant data2. On data arrival, compute route contention3. If there is a contention on my path4. If TTC is close to TTA and driver is not braking5. issue WARNING6. Else if TTC is less than TTA7. Delegate task to Mitigation unit8. Else go to (1)9. Else go to (1)10. Wait until pass the intersection, go to (1)

ROUTE CONTENTION

Two vehicles at (x1; y1), (x2; y2), are moving at speeds v1, v2, and directions µ1, µ2 respectively. In our algorithm, we first compute the expected path intersection (x+; y+) by using both vehicles’ headings and locations.

x+ = ( y 2 - y 1) - ( x 2 tan µ 2 - x 1 tan µ 1) tan µ1 - tan µ2y+ = ( x 2 - x 1) - ( y 2 cot µ 2 - y 1 cot µ 1) cot µ1 - cot µ2

The expected time-to-intersection (TTX) for each vehicle is compared. The expected TTXs of both vehicles are then computed. Once a vehicle cleared the intersection, its TTX becomes negative. If the two vehicles are expected to get to their path intersection point at the same time, i.e., TTX1 = TTX2, then there is a route contention. Once there is a route contention, the TTX is the same as time-to-collision (TTC).

TIME TO AVOIDANCE

Once a contention is discovered, the algorithm needs to decide whether to issue a warning. There are two reasons to hold back even if there is route contention. One is because the driver has already taken appropriate action, e.g., the brake was applied already. The other is because there is still plenty of time for the vehicle to reach the intersection, i.e., it is too early to issue the warning immediately.

HARDWARE ARCHITECTURE

The algorithm requires knowledge of the vehicle location, velocity, and other vehicle state information, In order to get this information; we attach a Global Positioning System (GPS) receiver to each vehicle. This gives us location and velocity information. Other vehicle state information are taken from the vehicle bus. The vehicle bus data includes brake state, brake pressure, steering wheel angle, throttle angle, RPM, differential wheel speed. Each vehicle is also equipped with a wireless system that supports ad hoc communication and enables the direct sharing of information between peers. An audio user interface is used to issue warnings as well as to receive commands from the driver. The embedded audio system is conversational in nature and uses a natural language system.

SEAT BELT BASED SAFE DRIVING SYSTEM This is a proposed system in which the driver and the passengers have to ensure that they have worn their respective seat belts for able to start the vehicle. This will lead to safety measures and the persons have to wear seat belts for be able to start the vehicle in question. This feature will be implemented in Real-Time i.e. the persons have to wear the seat belts throughout the journey and not only when they have to start the vehicle. If the seat belts are detached, then the microcontroller based circuitry gets the alert of such an action which will immediately put the vehicle’s ignition to stop, thus stopping the vehicle. In this system we have also proposed the feature of sending an alert SMS in case of any accident to the family members and also a real time tracking on Google Map. The feature of GPS is re-defined in such a manner that the relatives will get the coordinates of the location where the vehicle is presently stationed on their mobile handsets.

HARDWARE ARCHITECTURE

The entire system will receive inputs from switch circuits which will be constructed on the seat belts. The design of seat belts is very crucial in this regard. We can either go for the design of seat belts which get activated on human touch or with the help of some electronic circuitry which will constantly monitor whether the seat belt is being worn in the correct manner or not. We have proposed to use AVR microcontroller for the above system. Basically these sensors shall be micro-switches which get actuated with little physical force. One more advancement or further scope of research can be done in the design of the body of the vehicle i.e. the outer body of the cars

can be designed which shall sense if the distance of the approaching/nearing vehicle is too close than what is considered as safe distance. Cameras can be placed at some optimum places around the car which can convey the information to the central processor which can then analyze the information based on Image processing techniques.

These switches inform the microcontroller regarding the accident and a pre-typed message shall be sent to the family members. The micro-controller is interfaced to a Bluetooth modem which sends the message to the mobile phone of the driver. One thing to be noted is that the cell phone should have the Bluetooth in the ON mode while driving; this is to ensure his/her own personal safety. When the seat belt is worn properly the message is displayed on the LCD screen, the micro-controller activates the relay via a relay driver. This relay in turns controls the ignition switch of the vehicle. The central processor will be run by a battery. We can devise a strategy in which the battery will derive some power from the battery of the vehicle. Another feature that can be added with this is the real-time location using GPS and the position can be found on the Google Map. The above system can also be extended to motorcycles wherein the biker has to wear his respective helmet for be able to start his bike.

ALGORITHM

1. Check if the seat belt is worn properly?? If yes go to step 2 else keep checking this condition.

2. Route the data through the micro-controller and activate the relay which in turn activates the ignition switch.

3. Read continuously the data from the micro-switches.

4. If the switches detect accident, activate the Bluetooth modem and send the pre-typed message to the mobile of the family members via the driver’s handset.

The members of the family will get the message on their handsets and will also get the coordinates of the vehicle where it is presently located. . They can then log on to the Internet where by entering the latitude & longitude, they can get the exact map of the place. An added feature that can be implemented is that the positioning of the camera on the deck of the car such that it can send images just with the small click on the Internet. The requirements are that mobile handset should be GPS, Bluetooth and camera enabled.

The intelligent seat-belt reminder system detects whether the occupants have worn their seat belts properly and if not, it creates a series of increasingly annoying visual and auditory alarms to encourage seat belt use.

MONITORING DRIVER VIGILANCE; DROWSINESS, FATIGUE AND INATTENTION

The detection of driver visual attention is very important for developing automatic systems that monitor the driver inattention, driver fatigue, and lack of sleep: a great number of fatalities occurring in motor vehicles could be avoided if these behaviors were detected and alarm signals were provided to the driver. A driver’s state of vigilance can also be characterized by indirect behaviours of the vehicle like lateral position, steering wheel movements, time to line crossing, etc. People in fatigue show some visual behaviours easily observable from changes in their facial features like eyes, head and face Computer vision can be a natural and non-intrusive technique to monitor driver’s vigilance. Vision based approaches rely on eye movements to estimate drowsiness levels. Video cameras mounted in the car track the eye closure speed, saccadic eye movements, and the head movements of the driver. Driver monitoring systems are currently emerging in passenger and commercial vehicles. There are obvious difficulties in applying these systems, particularly eye tracking devices, to the motorcycle, and the extent to which motorcyclist fatigue, inattention and distraction.

PREVIOUS WORKS

Many efforts have been reported in the literature for the development of an active safety system for reducing the number of automobiles accidents due to reduced vigilance. Drowsiness in drivers can be generally divided into the following categories: sensing of physiological characteristics, sensing of driver operation, sensing of vehicle response, monitoring the response of driver. Among these methods, the techniques based on human physiological phenomena are the most accurate. This technique is implemented in two ways: measuring changes in physiological signals, such as brain waves, heart rate, and eye blinking; and measuring physical changes such as sagging posture, leaning of the driver’s head and the open/closed states of the eyes. The first technique, while most accurate, is not realistic, since sensing electrodes would have to be attached directly on to the driver’s body, and hence be annoying and distracting to the driver. In addition, long time driving would result in perspiration on the sensors, diminishing their ability to monitor accurately. The second technique is well-suited for real world driving conditions since it can be non-intrusive by using video cameras to detect changes. Driver operation and vehicle behavior can be implemented by monitoring the steering wheel movement, accelerator or brake patterns, vehicle speed, lateral acceleration, and lateral displacement. These too are nonintrusive ways of detecting drowsiness, but are limited to vehicle type and driver condition. The final technique for detecting drowsiness is by monitoring the response of the driver. This involves periodically requesting the driver to send a response to the system to indicate alertness. The problem with this technique is that it will eventually become tiresome and annoying to the driver.

The systems are generally based on eyes close count & yawning count of the driver. By monitoring the eyes and mouth, it is believed that the symptoms of driver fatigue can be detected early enough to avoid a car accident. The eye blink frequency increases beyond the normal rate in the fatigued state. In addition, micro sleeps that are the short periods of sleep lasting 3 to 4 seconds are the good indicator of the fatigued state, but it is difficult to predict the driver fatigue accurately or reliably based only on a single driver behavior. Additionally, the changes in a driver’s performance are more complicated and not reliable, so in this system the second parameter is also considered which is called the yawning count.

In order to detect fatigue the facial expression parameters must be extracted first. As fatigue level can be properly characterized by eyes and mouth movements, a vision sensor can be used to recognize and track the eyes and the mouth. A normal video-

camera can be used which can be kept on the deck of the car but the necessary condition is that the environment is bright enough. Here, eye closing count, and yawn count in successive frames can be detected using a web camera. In real time implementation if 30 fps is considered then successive frames have same information , so instead of considering all frames of video files, some frames should be selected such that which gives more information but less computational requirements. In this proposed system instead of analyzing complete frame of video file, eyes and mouth portion are separated after detecting face area, the facial features in these regions are considered in detail and corresponding eyes closing count & yawning count can be obtained using correlation method and for this type of operation Digital Image Processing filtering and segmentation process has to be carried out.

SYSTEM OVERVIEW

The complete block diagram representation of the proposed system is as shown in figure 1 while the flowchart of the proposed system of The Drowsy Driver Detection System is shown in Figure.2 After inputting a facial image; the skin colour based algorithm is applied to detect the face in the image. The eyes portion and mouth portion of the image is separated from which the open or closed state of the eyes are detected along with yawning count. These two parameters which are the output of the DIP Module are given as the input to the Hybrid Intelligent System which is a combination of neural network and Genetic Algorithm, which can give corresponding fatigue indication. Depending on the fatigue, the system draws the conclusion that the driver is in the fatigued state and issues a warning signal.

BLOCK DIAGRAM

FLOWCHART

In this system, AVI file is used which is converted to frames and random frames are selected from it for further processing. The next step will be of eye and lip detection. Eyes are located by performing some morphological operations on the face. This is done by converting the image to a binary image, based on threshold. In the binary image there are two significant intensity changes that can be seen. The first intensity change is the eyebrow, and the next change is the upper edge of the eye. The state of the eyes (whether it is open or closed) is determined by distance between the two intensity changes. When the eyes are closed, the distance i.e. the no. of white pixels between the two intensity changes is larger as compared to when the eyes are open. The parameter extraction is performed by DIP Module which is then provided to Genetic process based Optimized Neural Network, which gives comparative result of fatigues. Human face localization and detection is often the first step in applications such as video surveillance, human computer interface, face recognition and /or facial expressions analysis and image database management. A neural network can solve a nonlinear complicated problem very simply and results in a reasonably accurate approximation of an unknown system.

ADVANCED DRIVER ASSISTANCE USING LANE DETECTION

Current driver assistance systems normally rely on the detection of objects, e.g., cars, in the own vehicle’s surrounding. In this contribution observation of the road environment with a particular focus on lanes is discussed. Lane-keeping assistance is investigated for the use in heavy trucks. Then, a combination of the information obtained by lane observation and by object information is discussed to obtain a more complete representation of the own vehicle’s driving environment.

First assistance systems, like Adaptive Cruise Control, rely on information provided by a single sensor. As progress advances, more complex perception methods are used. This contribution describes the utilization of a lane-tracking camera together with object sensors (e.g., radar) for driver assistance systems. In the first application case, the camera observation of the lane is used for lane-keeping assistance by controlling among others an active steering actuator. In the second application case, the lane observation is combined with object information to yield better environment representation that can be used for numerous driving assistance tasks.

CONCLUSION

Thus, we have reviewed several existing and emerging ITS technologies in-vehicle systems that could enhance safety for vehicles. There are advanced driver assistance system, intelligent speed adaptation, driver monitoring system, collision warning and avoidance system. We have proposed our idea of a seat belt based safe driving system. We have also proposed the implementation of sending of Alert SMS in case of an accident. Suitable algorithm has been proposed for reducing the number of collisions on busy intersection roads using GPS technology. However, there is a need for the development of standards for the design of ITS technologies for motorcycles, as there is for the design of ITS technologies for other vehicles.

REFERENCES

[1]. “Intelligent Monitoring System for Driver’s Alertness (A vision based approach)”R.S. Parsai, Dr.P.R.Bajaj, KES 2007 International Conf.Sept-07, Italy.

[2]. “Monitoring Driver Fatigue Using Facial Analysis Techniques” Singh, Sarbjit and Papanikolopoulos, IEEE Intelligent Transport System Proceedings, 1999, pp. 314- 318.

[3]. “Driver Fatigue Detection using Genetic Algorithm.”S. Jin , S.-Y. Park • J.-J. Lee, 11th International Symposium on Artificial Life and Robotics, Oita, Japan, January 23–25, 2006.

[4] Minoru Tamura, Hideaki Inoue, Takayuki Watnabe and Naoki Maruko. Research on a Brake Assist System with a Preview Function. SAE Paper 2001-01-0357

[5]. Development of an Adaptive Cruise Control with Stop-and-Go Capability, SAE Paper 2001-01-0807

[6]. Berthold Ulmer. VITA II – Active Collision Avoidance in Real Traffic. 1994

[7]. Bo Zhu. Potential Effects on Accidents from Forward Collision Warning/Avoidance System. Master thesis at Linköping University, LITH-ITN-EX- 150-SE, 2001.

[8]. Almqvist, S., and Nygård, M., 1997. Dynamic speed adaptation: A field trial with automatic speed adaptation in an urban area (Bulletin 154). Lund, Sweden: Lund Institute of Technology, University of Lund.

[9]. Ararat, O., Kural, E., and Aksun, G. B., 2006. Development of a collision warning system for adaptive cruise control vehicles using a comparison analysis of recent algorithms. IEEE Intelligent Vehicles Symposium, Tokyo, Japan, 194 – 198.

[10]. Batista, J., 2007. A Drowsiness and point of attention monitoring system for driver vigilance. 2007 IEEE Intelligent Transportation Systems Conference Seattle, WA, USA, WeA1.3, 702 –708.