Faculty of engineering

Department of civil and structural engineering

KKKA 6424

INTELIGENT URBAN TRAFFIC CONTROL SYSTEM

Ir. Dr. Riza Atiq Abdullah O.K. Rahmat

ASSIGNMENT 5

IMAGE PROCESSING

DONE BY

MOHANAD JAAFAR TALIB – P71085

VIDEO CAMERAS

Video cameras are either analogue or digital, which means that they work on the basis of sending analogue or digital signals to a storage device such as a video tape recorder or desktop computer or laptop computer.

ANALOGUE

Can record straight to a video tape recorder which are able to record analogue signals as pictures. If the analogue signals are recorded to tape, then the tape must run at a very slow speed in order to operate continuously. This is because in order to allow a three hour tape to run for 24 hours, it must be set to run on a time lapse basis which is usually about four frames a second. In one second, the camera scene can change dramatically. A person for example can have walked a distance of 1 meter, and therefore if the distance is divided into four parts, i.e. four frames or "snapshots" in time, then each frame invariably looks like a blur, unless the subject keeps relatively still.

Analogue signals can also be converted into a digital signal to enable the recordings to be stored on a PC as digital recordings. In that case the analogue video camera must be plugged directly into a video capture card in the computer, and the card then converts the analogue signal to digital. These cards are relatively cheap, but inevitably the resulting digital signals are compressed 5:1 (MPEG compression) in order for the video recordings to be saved on a continuous basis.

Another way to store recordings on a non-analogue media is through the use of a digital video recorder (DVR). Such a device is similar in functionality to a PC with a capture card and appropriate video recording software. Unlike PCs, most DVRs designed for CCTV purposes are embedded devices that require less maintenance and simpler setup than a PC-based solution, for a medium to large number of analogue cameras.

DIGITAL

These cameras do not require a video capture card because they work using a digital signal which can be saved directly to a computer. The signal is compressed 5:1, but DVD quality can be achieved with more compression (MPEG-2 is standard for DVD-video, and has a higher compression ratio than 5:1, with a slightly lower video quality than 5:1 at best, and is adjustable for the amount of space to be taken up versus the quality of picture needed or desired). The highest picture quality of DVD is only slightly lower than the quality of basic 5:1-compression DV.

Saving uncompressed digital recordings takes up an enormous amount of hard drive space, and a few hours of uncompressed video could quickly fill up a hard drive. Holiday uncompressed recordings may look fine but one could not run uncompressed quality recordings on a continuous basis. Motion detection is therefore sometimes used as a work around solution to record in uncompressed quality.

However, in any situation where standard-definition video cameras are used, the quality is going to be poor because the maximum pixel resolution of the image chips in most of these devices is 320,000 pixels (analogue quality is measured in TV lines but the results are the same); they generally capture horizontal and vertical fields of lines and blend them together to make a single frame; the maximum frame rate is normally 30 frames per second.

That said, multi-megapixel IP-CCTV cameras are coming on the market. Still quite expensive, but they can capture video images at resolutions of 1, 2, 3, 5 and even up to 11 Mpix. Unlike with analogue cameras, details such as number plates are easily readable. At 11 Mpix, forensic quality images are made where each hand on a person can be distinguished. Because of the much higher resolutions available with these types of cameras, they can be set up to cover a wide area where normally several analogue cameras would have been needed.

Network

IP cameras or network cameras are analogue or digital video cameras, plus an embedded video server having an IP address, capable of streaming the video (and sometimes, even audio).

Because network cameras are embedded devices, and do not need to output an analogue signal, resolutions higher than CCTV analogue cameras are possible. A typical analogue CCTV camera has a PAL (768×576 pixels) or NTSC (720×480 pixels), whereas network cameras may have VGA (640×480 pixels), SVGA (800×600 pixels) or quad-VGA (1280×960 pixels, also referred to as "megapixel") resolutions.

An analogue or digital camera connected to a video server acts as a network camera, but the image size is restricted to that of the video standard of the camera. However, optics (lenses and image sensors), not video resolution, are the components that determine the image quality.

Network cameras can be used for very cheap surveillance solutions (requiring one network camera, some Ethernet cabling, and one PC), or to replace entire CCTV installations (cameras become network cameras, tape recorders become DVRs, and CCTV monitor become computers with TFT screens and specialized software. Digital video manufacturers claim that turning CCTV installations into digital video installations is inherently better).

IMAGE PROCESSING

Image processing refers to processing of a 2D picture by a computer. Basic definitions:

An image defined in the “real world” is considered to be a function of two real variables, for example, a(x, y) with a as the amplitude (e.g. brightness) of the image at the real coordinate position (x, y).

Modern digital technology has made it possible to manipulate multi-dimensional signals with systems that range from simple digital circuits to advanced parallel computers. The goal of this manipulation can be divided into three categories:

Image Processing (image in -> image out)

Image Analysis (image in -> measurements out)

Image Understanding (image in -> high-level description out)

An image may be considered to contain sub-images sometimes referred to as regions-of-interest, ROIs, or simply regions. This concept reflects the fact that images frequently contain collections of objects each of which can be the basis for a region. In a sophisticated image processing system it should be possible to apply specific image processing operations to selected regions. Thus one part of an image (region) might be processed to suppress motion blur while another part might be processed to improve color rendition. Sequence of image processing:

Most usually, image processing systems require that the images be available in digitized form, that is, arrays of finite length binary words. For digitization, the given Image is sampled on a discrete grid and each sample or pixel is quantized using a finite number of bits. The digitized image is processed by a computer. To display a digital image, it is first converted into analog signal, which is scanned onto a display.

Closely related to image processing are computer graphics and computer vision. In computer graphics, images are manually made from physical models of objects, environments, and lighting, instead of being acquired (via imaging devices such as cameras) from natural scenes, as in most animated movies. Computer vision, on the other hand, is often considered high-level image processing out of which a machine/computer/software intends to decipher the physical contents of an image or a sequence of images (e.g., videos or 3D full-body magnetic resonance scans).

In modern sciences and technologies, images also gain much broader scopes due to the ever growing importance of scientific visualization (of often large-scale complex scientific/experimental data). Examples include microarray data in genetic research, or real-time multi-asset portfolio trading in finance.

Before going to processing an image, it is converted into a digital form. Digitization includes sampling of image and quantization of sampled values. After converting the image into bit information, processing is performed. This processing technique may be Image enhancement, Image restoration, and Image compression.

Additional equipment such as computer and communication system

THERMOGRAPHY

Infrared thermography (IRT), thermal imaging, and thermal video are examples of infrared imaging science. Thermographic camerasdetect radiation in the infrared range of the electromagnetic spectrum (roughly 9,000–14,000 nanometers or 9–14 µm) and produce images of that radiation, called thermograms. Since infrared radiation is emitted by all objects above absolute zero according to the black body radiation law, thermography makes it possible to see one's environment with or without visible illumination. The amount of radiation emitted by an object increases with temperature; therefore, thermography allows one to see variations in temperature. When viewed through a thermal imaging camera, warm objects stand out well against cooler backgrounds; humans and other warm-blooded animals become easily visible against the environment, day or night. As a result, thermography is particularly useful to military and other users ofsurveillance cameras.