Object detection, as of one the most fundamental and challenging problems in computer vision, has received great attention in recent years. Its development in the past two decades can be regarded as an epitome of computer vision history. If we think of today's object detection as a technical aesthetics under the power of deep learning, then turning back the clock 20 years we would witness the wisdom of cold weapon era. This paper extensively reviews 400+ papers of object detection in the light of its technical evolution, spanning over a quarter-century's time (from the 1990s to 2019). A number of topics have been covered in this paper, including the milestone detectors in history, detection datasets, metrics, fundamental building blocks of the detection system, speed up techniques, and the recent state of the art detection methods. This paper also reviews some important detection applications, such as pedestrian detection, face detection, text detection, etc, and makes an in-deep analysis of their challenges as well as technical improvements in recent years.

Object Detection in 20 Years: A Survey

This paper proposes a novel system for the automatic detection and recognition of traffic signs. The proposed system detects candidate regions as maximally stable extremal regions (MSERs), which offers robustness to variations in lighting conditions. Recognition is based on a cascade of support vector machine (SVM) classifiers that were trained using histogram of oriented gradient (HOG) features. The training data are generated from synthetic template images that are freely available from an online database; thus, real footage road signs are not required as training data. The proposed system is accurate at high vehicle speeds, operates under a range of weather conditions, runs at an average speed of 20 frames per second, and recognizes all classes of ideogram-based (nontext) traffic symbols from an online road sign database. Comprehensive comparative results to illustrate the performance of the system are presented.

Real-Time Detection and Recognition of Road Traffic Signs

In this letter, a new satellite image contrast enhancement technique based on the discrete wavelet transform (DWT) and singular value decomposition has been proposed. The technique decomposes the input image into the four frequency subbands by using DWT and estimates the singular value matrix of the low-low subband image, and, then, it reconstructs the enhanced image by applying inverse DWT. The technique is compared with conventional image equalization techniques such as standard general histogram equalization and local histogram equalization, as well as state-of-the-art techniques such as brightness preserving dynamic histogram equalization and singular value equalization. The experimental results show the superiority of the proposed method over conventional and state-of-the-art techniques.

Satellite Image Contrast Enhancement Using Discrete Wavelet Transform and Singular Value Decomposition

In this article, an efficient method for the pattern synthesis of the linear antenna arrays with the prescribed null and multi-lobe Beamforming is presented. Multi-lobe pattern and adaptive nulling of the pattern is achieved by controlling only the phase of each array element. The proposed method is based on the Sequential Quadratic Programming (SQP) algorithm and the linear antenna array synthesis was modelled as a multi-objective optimization problem. Multi-objective optimization is concerned with the maximization (or minimization) of a vector of objectives functions in the directions of desired signal that can be subject of a number of constraints (in our case, the constraints can be imposed as the null in the direction of interfering signal). To verify the validity of the technique, several illustrative examples of uniform excited array patterns with the main beam is placed in the direction of the useful signal and null is placed in the direction of potential interferers, and multi-beam patterns are demonstrated.

/pdf/smart-antenna-array-patterns-synthesis-null-steering-and-2q2a8fahj2.pdf

Smart antenna array patterns synthesis: null steering and multi-user beamforming by phase control

This paper presents a road signs detection and classification system based on a three-step algorithm composed of color segmentation, shape recognition, and a neural network. The final goal of this algorithm is to detect and classify almost all road signs present along Italian roads. Color segmentation was suggested by the aim to achieve real time execution, since color-based segmentation is faster than the one based on shape. In order to save computational time, only the RGB color space, directly supplied by the chosen camera, or color spaces that can be obtained with linear transformations, are considered. Two different methods are used for shape detection, one is based on pattern matching with simple models and the other one is based on edge detection and geometrical cues. The complete set of signs taken in account has been divided in several categories according to their shape and color. Finally for each road signs set a neural network is built and trained.

/pdf/real-time-road-signs-recognition-3u2juv5tqf.pdf

Real Time Road Signs Recognition

This work is a part of a smart system that can be used in autonomous vehicles or can assist drivers in locating road signs. The detection technique includes histogram equalization, light control and color segmentation. In this technique, both the HSV and the YUV color spaces are incorporated to achieve better segmentation results than that of one color space techniques.

Road traffic sign detection in color images

A new numerical technique is proposed for array pattern synthesis to suppress multiple interference signals using the position perturbations of linear antenna elements. The element position perturbations are computed using the iterative Levenberg–Marquardt (LM) algorithm. Pattern synthesis with suppressed sectors is achieved using full control and partial control of the edge elements. When the number of array elements is too large, partial control of array elements will reduce the cost and complexity. The results show that the proposed technique is efficient in imposing multiple narrow and/or wide suppressed sectors in the array pattern for narrow and wide interferences, respectively.

Interference suppression by element position control of phased arrays using LM algorithm

This work presents a numerical technique for sector nulling using phase-only perturbations of the array elements. The phases of the elements are computed using the Levenberg–Marquardt algorithm. The proposed numerical technique is based on a template of a prescibed array pattern and a relative error for the cost function that is used in the Levenberg–Marquardt algorithm. The results show that the proposed numerical technique is suitable for the design of the general array pattern requirements due to the use of the template and the relative error.

Phase-Only Control for Antenna Pattern Synthesis of Linear Arrays Using the Levenberg-Marquardt Algorithm

A new analytical synthesis technique is developed for the phase-only control of linear antenna arrays and is based on the Schelkunoff's unit circle. The array factor is formulated as an array polynomial in the complex z -plane and as a product of corresponding subpolynomials such that their roots are located on the unit circle. A constraint is derived such that the expansion of the subpolynomials yields current excitations with unity magnitudes. In general, the constraint of phase-only control forces some element excitations to be zero for an arbitrary number of array elements. The subpolynomial with the largest degree is used to synthesize the main beam characteristics. The null steering for interference suppression is obtained by using only one subpolynomial to steer only one null. The results verify the developed analytical solution to synthesize the prescribed patterns using the phase shifters of the linear antenna arrays.

Analytical array polynomial method for linear antenna arrays with phase-only control

This paper presents a method for linear array pattern synthesis with multiple suppressed sectors using phase-only control of the antenna elements. Large phase perturbations are obtained by solving the nonlinear problem using an iterative procedure with linear programming. This technique can impose symmetrical and non-symmetrical suppressed sectors in the perturbed pattern. The full phase-only control is accomplished as well as the partial control of the edge elements. The partial control leads to a significant reduction in the number of phase shifters used for sector suppression as compared to the full control implementation.

/pdf/pattern-nulling-by-iterative-phase-perturbation-5fzdmqo014.pdf

M. J. Mismar

Papers

Road traffic sign detection in color images

Interference suppression by element position control of phased arrays using LM algorithm

Phase-Only Control for Antenna Pattern Synthesis of Linear Arrays Using the Levenberg-Marquardt Algorithm

Analytical array polynomial method for linear antenna arrays with phase-only control

Pattern Nulling by Iterative Phase Perturbation