All posts by Windmill Software

Windmill Software specialise in data acquisition and control. They publish a monthly newsletter, called Monitor, giving useful information on sensors and systems - http://www.windmill.co.uk/newsletter.html

Vehicle Sensing: Ten Technologies to Measure Traffic

There are a surprising number of ways available today to count vehicles, and it is interesting to see how the technology has progressed and the options available.

ManualVideoPneumatic TubesPiezoelectricInductive LoopMagneticAcousticPassive InfraredMicrowave


Manual counts

A simple but accurate method of traffic counting comprises people manually counting vehicles.

A person either uses an electronic hand held counter or records data using a tally sheet.

They may stand at the side of the road, or, more commonly watch a video of the road and count from that.

In tests manual vehicle counting was 99% accurate.

With manual counts a small sample of data is taken – typically over less than a day – and results are extrapolated for the rest of the year or season.


Video Vehicle Detection

Obviously manual counting is labour intensive. Systems are now available that will automatically analyse the video pictures as cars are passing underneath, detecting cars with a similar accuracy to that of people watching the video.

This vehicle counting method has several advantages over other automatic systems. It is cost-effective as it can count in many directions at once: only one camera is needed for several lanes or exits at a junction. It is easy to add or modify the zones through which vehicles are counted from an office PC.

Local video analytics minimises bandwidth use. Traffic counts are uploaded in real-time via the internet, so traffic engineers can view live (down to 15 minute intervals for example) and historic counts from their web browsers.

Counts are easily verified simply by watching the video and checking the automated counts.

Video traffic counting typically takes place continuously, year round, giving precise figures.

Contact us for more information.


Pneumatic Road tube counting

This has for many years been a popular method of vehicle sensing.

Here one or more rubber hoses are stretched across the road and connected at one end to a data logger. The other end of the tube is sealed. When a pair of wheels hits the tube, air pressure in the squashed tube activates the data logger which records the time of the event.

A pair of tubes can be stretched across several lanes of traffic. The data logger can establish vehicle direction by recording which tube is crossed first. This has the drawback that if two vehicles cross the tubes at the same time then the direction can’t be accurately determined. Should two cars be very close together when they cross the tubes, the system may see them as one multiaxle vehicle.

Vendors claim an accuracy of 99%. Studies show though, that the absolute error of a typical 15-minute count averaged closer to ten percent. This suggests that the level of inaccuracy is being masked by the positive and negative counting errors cancelling each other out.

The counts need to be physically downloaded onto a computer from the loggers at the roadside. At least one road tube is needed for each direction on every road or junction at which you want to count. Installation requires working within the traffic lane.

Road tubes work well for short duration counts on lower volume roads. They are not as effective on higher volume, multi-lane highways.


Piezoelectric Sensor

Piezoelectric sensors collect data by converting mechanical energy into electrical energy. The piezoelectric sensor is mounted in a groove cut into road’s surface.

When a car drives over the piezoelectric sensor, it squeezes it and causes an electric potential – a voltage signal. The size of the signal is proportional to the degree of deformation. When the car moves off, the voltage reverses.

This change in voltage can be used to detect and count vehicles.

The counting device which is connected to the sensors is housed in an enclosure by the side of the road. Data may be collected locally via an Ethernet or RS232 connection to a laptop, or may be transmitted by modem.

Piezoelectric traffic counter
Piezoelectric traffic counter by the side of the road


Inductive Loop

An inductive loop is a square of wire embedded into or under the road. The loop utilizes the principle that a magnetic field introduced near an electrical conductor causes an electrical current to be induced. In the case of traffic monitoring, a large metal vehicle acts as the magnetic field and the inductive loop as the electrical conductor. A device at the roadside records the signals generated.


Magnetic Sensor

This detects vehicles by measuring the change in the earth’s magnetic field as the vehicles pass over the detector.

The sensor is either buried in the road, or enclosed in a box by the side of the road.

If vehicles are following each other very closely, the magnetic detector may have difficulty discriminating between them.


Acoustic detector

This detects vehicles by the sound created as the vehicle passes.

The sensor is mounted on a pole pointing down towards the traffic. It can collect counts for one or more travel lanes.

Some can communicate their counts wirelessly.


Passive Infrared

Passive infrared devices detect vehicles by measuring the infrared energy radiating from the detection zone. When a vehicle passes the energy radiated changes and the count is increased.

Slow changes in road surface temperature, caused by changing weather conditions, are ignored.

Lane coverage is limited to one to two lanes.


Doppler and Radar Microwave Sensors

Doppler microwave detection devices transmit a continuous signal of low-energy microwave radiation at a target area and then analyze the reflected signal. The detector registers a change in the frequency of waves occurring when the microwave source and the vehicle are in motion relative to one another. This allows the device to detect moving vehicles.

Radar is capable of detecting distant objects and determining their position and speed of movement. With vehicle detection, a device directs high frequency radio waves at the roadway to determine the time delay of the return signal, thereby calculating the distance to the detected vehicle.


References

An Investigation on the Manual Traffic Count Accuracy, Procedia – Social and Behavioral Sciences 12/2012; 43:226-231. DOI: 10.1016/j.sbspro.2012.04.095

Accuracy of Pneumatic Road Tube Counters. McGowen and Sanderson. A report prepared for the 2011 Western District Annual Meeting Institute of Transportation Engineers Anchorage, AK May 2011.

Traffic Monitoring Guide, 2013, U.S. Department of Transportation

Photo credits: Retail Sensing, Louis van Senden [CC BY-SA 4.0]

Solved: The 5 Challenges of Human Sensing

Researchers have identified five technology challenges in human sensing systems, all of which have been solved by Retail Sensing systems.

Thiago Teixeira, Gershon Dublon and Andreas Savvide of Yale University and Massachusetts Institute of Technology addressed the increasingly common requirement of computer systems to extract information about the people present in an environment. They pin-pointed five requirements that the most accurate systems need to meet.

1. Environmental Variations

Unexpected or sudden changes in environmental conditions are common sources of errors in some real-world scenarios. Radar signals, for instance, can be dampened by rain or fog. A large portion of the computer vision literature is aimed at dealing with variations in lighting, shadows and so on.

Our human sensing systems have been specifically designed to cope with situations with dark shadows and changes in lighting. Each sensing position can be configured for the particular conditions at that location. Tests show that video technology achieves over 98% accuracy in human sensing.

2. Similarity to Background Signal

“Clearly, separating a person from the background signal is a core requirement for human-sensing” the scientists write. Our technology freezes the background at the moment a person enters and easily distinguishes the moving person from her surroundings.

3. Appearance variability and unpredictability

People look different and wear a vast assortment of different types of clothes and hats, they push trollies and pushchairs, and carry back-packs and hand-bags. This at first looks like a problem for video systems, but is solved by the software converting an individual to a “blob”, as shown in the video below.

4. Similarity to Other People

Some tracking systems use identifying features of a person to track them – presenting a challenge if people are all wearing similar clothes or uniforms. Our technology follows the “blob” we have identified as person so it doesn’t matter if everyone looks alike. Each blob is seen as unique and distinguished from the others, even in crowded situations.

5. Active Deception

The researchers’ final point is when a human sensing system may be deliberately debilitated, perhaps by people walking slowly to fool motion sensors, covering a break beam with their hands or turning the lights off to fool the cameras. A CCTV system lets users remotely play back the video over the internet to see why counting has suddenly stopped and rectify the problem.

The researchers conclude that the best system is computer vision, saying “Computer vision is far ahead from other instrumented modalities not only with respect to spatial-resolution and precision metrics, but also in terms of having the most field-tested solutions“.

Further Reading

You can read the research at
A Survey of Human-Sensing: Methods for Detecting Presence, Count, Location, Track, and Identity T TEIXEIRA, G DUBLON, A SAVVIDES
ENALAB technical report