Mohammad Izadi

Three-Dimensional Polygonal Building Model Estimation From Single Satellite Images

This paper introduces a novel system for automatic detection and height estimation of buildings with polygonal shape roofs in singular satellite images. The system is capable of detecting multiple flat polygonal buildings with no angular constraints or shape priors. The proposed approach employs image primitives such as lines, and line intersections, and examines their relationships with each other using a graph-based search to establish a set of rooftop hypotheses. The height (mean height from rooftop edges to the ground) of each rooftop hypothesis is estimated using shadows and acquisition geometry. The potential ambiguities in identification of shadows in an image and the uncertainty in identifying true shadows of a building have motivated for a fuzzy logic-based approach that estimates buildings heights according to the strength of shadows and the overlap between identified shadows in the image and expected shadows according to the building profile. To reduce the time complexity of the implemented system, a maximum number of eight sides for polygonal rooftops is assumed. Promising experimental results verify the effectiveness of the presented system with overall mean shape accuracy of 94% and mean height error of 0.53 m on QuickBird satellite (0.6 m/pixel) imageries.

Robust Weighted Graph Transformation Matching for Rigid and Nonrigid Image Registration

This paper presents an automatic point matching algorithm for establishing accurate match correspondences in two or more images. The proposed algorithm utilizes a group of feature points to explore their geometrical relationship in a graph arrangement. The algorithm starts with a set of matches (including outliers) between the two images. A set of nondirectional graphs is then generated for each feature and its K nearest matches (chosen from the initial set). Using the angular distances between edges that connect a feature point to its K nearest neighbors in the graph, the algorithm finds a graph in the second image that is similar to the first graph. In the case of a graph including outliers, the algorithm removes such outliers (one by one, according to their strength) from the graph and re-evaluates the angles until the two graphs are matched or discarded. This is a simple intuitive and robust algorithm that is inspired by a previous work. Experimental results demonstrate the superior performance of this algorithm under various conditions, such as rigid and nonrigid transformations, ambiguity due to partial occlusions or match correspondence multiplicity, scale, and larger view variation.

Robust region-based background subtraction and shadow removing using color and gradient information

In this paper, a novel algorithm for foreground detection and shadow removal is presented. The proposed method employs a region-based approach by processing two foregrounds resulted from gradient-and color-based background subtraction methods. The performance of the system is compared against conventional approaches for five indoor and outdoor video sequences. Experimental results confirm that the detection rate exceeds 90%, and the robustness is greatly improved.

Automatic Building Detection in Aerial Images Using a Hierarchical Feature Based Image Segmentation

This paper introduces a novel automatic building detection method for aerial images. The proposed method incorporates a hierarchical multilayer feature based image segmentation technique using color. A number of geometrical/regional attributes are defined to identify potential regions in multiple layers of segmented images. A tree-based mechanism is utilized to inspect segmented regions using their spatial relationships with each other and their regional/geometrical characteristics. This process allows the creation of a set of candidate regions that are validated as rooftops based on the overlap between existing and predicted shadows of each region according to the image acquisition information. Experimental results show an overall shape accuracy and completeness of 96%.

High dynamic range pixel architecture for advanced diagnostic medical x-ray imaging applications

The most widely used architecture in large-area amorphous silicon (a-Si) flat panel imagers is a passive pixel sensor (PPS), which consists of a detector and a readout switch. While the PPS has the advantage of being compact and amenable toward high-resolution imaging, small PPS output signals are swamped by external column charge amplifier and data line thermal noise, which reduce the minimum readable sensor input signal. In contrast to PPS circuits, on-pixel amplifiers in a-Si technology reduce readout noise to levels that can meet even the stringent requirements for low noise digital x-ray fluoroscopy (<1000 noise electrons). However, larger voltages at the pixel input cause the output of the amplified pixel to become nonlinear thus reducing the dynamic range. We reported a hybrid amplified pixel architecture based on a combination of PPS and amplified pixel designs that, in addition to low noise performance, also resulted in large-signal linearity and consequently higher dynamic range [K. S. Karim et ...

Low-noise pixel architecture for advanced diagnostic medical x-ray imaging applications

The most widely used architecture in large-area amorphous silicon (a-Si) flat panel imagers is a passive pixel sensor (PPS), which consists of a detector element and a readout switch. While the PPS has the advantage of being compact and amenable toward high-resolution imaging, reading small PPS output signals requires external column charge amplifiers that produce additional noise and reduce the minimum readable sensor input signal. In contrast, on-pixel amplifiers in a-Si technology reduce readout noise by decoupling off-pixel noise sources, such as external charge amplifier and data line noise, from the sensor input. The off-pixel noise is reduced by the charge gain of the pixel amplifier, allowing for low-noise performance. Theoretical calculations and simulations of gain, linearity, metastability, pixel area requirements and noise indicate the applicability of the amplified a-Si pixel architectures for low-exposure, real-time fluoroscopy. In addition, the detailed noise results allow for the computation of noise performance as a function of transistor dimensions for both amorphous silicon and polysilicon technologies, allowing the designer to choose appropriate device dimensions when designing flat-panel imaging circuits.

An a-Si Active Pixel Sensor (APS) Array for Medical X-ray Imaging

Active pixel sensor (APS) circuits are an alternate to passive pixel sensor (PPS) circuits, which, while common in CMOS technology, have yet to be incorporated into commercial amorphous silicon (a-Si) large-area imagers. A proof-of-concept 64 × 64 APS array for low-exposure medical X-ray imaging is fabricated in a-Si technology and mated with an amorphous selenium photoconductor. Modulation transfer function (MTF) response and transient response for the APS imager indicate significant charge trapping at the top insulator/a-Se interface. MTF response indicates an effective fill factor of 94.5 % for a geometric fill factor of 57% at an electric field strength of 10 V/μm. Signal-to-noise ratio (SNR) performance from the prototype imager is comparable to a state-of-the-art commercially available a-Si PPS X-ray imager for X-ray exposures down to 1.5 μR using an RQA5 standard fluoroscopic characterization beam. Pixel design and fabrication process improvements are suggested to improve the SNR performance of the APS imager below 1.5 μR.

Noise analysis of fault tolerant active pixel sensors

As digital imagers grow in pixel count and area, the ability to correct for pixel defects becomes more important. A fault tolerant active pixel sensor (APS) has previously been designed and fabricated that can correct for stuck high and stuck low defects. Analyses of the pixel noise for a standard APS and a fault tolerant APS are presented that consider reset noise, photocurrent shot noise, dark current shot noise, transistor thermal noise, transistor flicker noise, operational amplifier noise, and feedback resistor thermal noise. Under worst case conditions (no illumination), the noise of the fault tolerant APS is 1.106 /spl times/ more than a standard APS. At a typical illumination level, the fault tolerant APS noise is nearly unchanged to that of a standard APS. Previous research has shown that the fault tolerant APS is more sensitive than a standard APS, thus the overall signal-to-noise ratio of the fault tolerant APS should be greater than the standard APS except under very low light conditions.

Noise optimisation analysis of an active pixel sensor for low-noise real-time X-ray fluoroscopy

Theoretical calculations and simulation results for the noise of a hybrid active pixel sensor designed for real-time digital fluoroscopy are presented. Noise performance is given as a function of transistor dimensions, allowing the designer to choose appropriate device dimensions when designing flat-panel imaging circuits. Optimal device dimensions are derived for minimising the input referred noise of the active pixel to meet the stringent requirements for low-noise digital X-ray fluoroscopy (<1000 noise electrons).

PLL-based frequency discriminator using the loop filter as an estimator

In this paper we present a new phase-locked-loop-based frequency discriminator architecture that performs both A/D conversion and frequency demodulation. In addition, the loop filter is designed as a linear estimator. Two forms of linear estimators are investigated. Simulation results show that for a minimum shift key signal at 400 MHz IF, the proposed frequency discriminator achieves an SNR improvement of up to 5 dB over a large variety of noise/fading conditions.