Varying Illumination Conditions Research Articles

Fractional derivative based Unsharp masking approach for enhancement of digital images

Image visual quality is severely degraded due to various environmental conditions, thus, leading to the loss in image details. Therefore, an image enhancement approach is required to improve the visual quality of images. In this paper, Unsharp Masking (UM) approach based on Riemann-Liouville (RL), Grunwald-Letnikov (GL), and Riesz fractional derivatives is proposed for the image enhancement. The fractional derivatives based UM approach sharpened the edges of an image while preserving its low and medium frequency details. Furthermore, the extra parameter of fractional derivative provides an additional degree of freedom, thus, increasing the effectiveness of the proposed approach. Extensive simulations carried out on several standard images of different sizes validated the performance of proposed approach in comparison to the existing techniques. The capability of the proposed approach is further confirmed by considering the test images with varying illumination conditions. Moreover, the comparative analysis performed in terms of quantitative measures such as Information Entropy (IE), Average Gradient (AG), Measure of Enhancement (EME), etc. confirmed that the proposed UM approach based on Riesz fractional derivative outperforms the existing state-of-the-art image enhancement techniques. Furthermore, the potential of the proposed approach is validated by considering its application in the medical images.

Active thermal imaging for immature citrus fruit detection

Yield mapping for citrus fruit is a challenging task due to factors such as varying illumination conditions, clustering, and occlusions. Mapping the yield for immature citrus fruit presents an additional challenge that is the colours of fruit and leaves are almost identical. Commonly used machine vision techniques using colour cameras become less effective for immature citrus fruit detection. This study explores a novel active thermal imaging method to tackle the problem of colour similarity between immature citrus fruit and leaves. In this study, a thermal camera was combined with a water spray system that applied water mist to citrus trees. The water mist caused temperatures of both the fruit and leaf surfaces to change but at different rates. Multiple parameters of the spray system were experimented with the goal to induce as much temperature differences as possible between fruit and leaf surfaces. The combined system was tested in a citrus grove for fruit detections. Deep learning models were built based on the active thermal imaging system and tracking and fruit counting algorithms were created to count fruit in thermal videos. A mean average precision of 87.2% was achieved by the models and an accuracy of 96% was achieved when comparing the number of fruit counted by the algorithms with the true number of fruit counted manually in the field.

Deep Convolutional Mixture Density Network for Inverse Design of Layered Photonic Structures.

Machine learning (ML) techniques, such as neural networks, have emerged as powerful tools for the inverse design of nanophotonic structures. However, this innovative approach suffers some limitations. A primary one is the nonuniqueness problem, which can prevent ML algorithms from properly converging because vastly different designs produce nearly identical spectra. Here, we introduce a mixture density network (MDN) approach, which models the design parameters as multimodal probability distributions instead of discrete values, allowing the algorithms to converge in cases of nonuniqueness without sacrificing degenerate solutions. We apply our MDN technique to inversely design two types of multilayer photonic structures consisting of thin films of oxides, which present a significant challenge for conventional ML algorithms due to a high degree of nonuniqueness in their optical properties. In the 10-layer case, the MDN can handle transmission spectra with high complexity and under varying illumination conditions. The 4-layer case tends to show a stronger multimodal character, with secondary modes indicating alternative solutions for a target spectrum. The shape of the distributions gives valuable information for postprocessing and about the uncertainty in the predictions, which is not available with deterministic networks. Our approach provides an effective solution to the inverse design of photonic structures and yields more optimal searches for the structures with high degeneracy and spectral complexity.

Superpixel-based segmentation algorithm for mature citrus.

With the decrease of agricultural labors and the increase in production costs, harvesting robots have become a research hotspot in recent years. To guide harvesting robots to pick mature citrus more precisely under variable illumination conditions, an image segmentation algorithm based on superpixel was proposed. Efficient simple linear iterative clustering (SLIC) algorithm which takes similarity of adjacent pixels into account was adopted to segment the images captured under variable illumination conditions into superpixels. The color and texture features of these superpixels were extracted and fused into feature vectors as descriptors to train backpropagation neural networks (BPNN) classifier in the next step. The adjacency information of superpixels was considered by calculating the global-local binary pattern (LBP) in R component images when extracting texture features. To accelerate the classification process, the mean of Cr-Cb image was utilized to find superpixels of interest which were regarded as candidates of citrus superpixels. These candidates were then classified by a pre-trained BPNN model with superpixel-level accuracy of 98.77% and pixel-level accuracy of 94.96%, while the average time to segment one image was 0.4778 s. Therefore, the results indicated that a superpixel-based segmentation algorithm toward citrus images had decent light robustness as well as high accuracy that could guide harvesting robot to pick mature citrus efficiently. Keywords: superpixel, image segmentation, BPNN, variable illumination, mature citrus DOI: 10.25165/j.ijabe.20201304.5607 Citation: Yang Q H, Chen Y Q, Xun Y, Bao G J. Superpixel-based segmentation algorithm for mature citrus. Int J Agric & Biol Eng, 2020; 13(4): 166–171.

Total generalized variation-based Retinex image decomposition

Human visual system (HVS) can perceive color under varying illumination conditions, and Retinex theory is precisely aimed to simulate and explain how the HVS perceives reflectance regardless of different illumination conditions. In this paper, we introduce a reflectance and illumination decomposition model for the Retinex problem via total generalized variation regularization and $$H^{1}$$ decomposition. The total generalized variation regularization ameliorates the staircasing artifacts that appear in the reflectance component of existing total variation-based models and $$H^{1}$$ norm guarantees smoother illumination. We analyze the existence and uniqueness of the proposed model and employ an alternating minimization scheme based on split Bregman iteration. We present numerous numerical experiments on both grayscale and color images to make comparisons with several state-of-the-art methods and demonstrate that our method is comparable both quantitatively and qualitatively.

Unsupervised Moving Object Detection in Complex Scenes Using Adversarial Regularizations

Moving object detection (MOD) is a fundamental step in many high-level vision-based applications, such as human activity analysis, visual object tracking, autonomous vehicles, surveillance, and security. Most of the existing MOD algorithms observe performance degradation in the presence of complex scenes containing camouflage objects, shadows, dynamic backgrounds, and varying illumination conditions, and captured by static cameras. To appropriately handle these challenges, we propose a Generative Adversarial Network (GAN) based on a moving object detection algorithm, called MOD_GAN. In the proposed algorithm, scene-specific GANs are trained in an unsupervised MOD setting, thereby enabling the algorithm to learn generating background sequences using input from uniformly distributed random noise samples. In addition to adversarial loss, during training, norm-based loss in the image space and discriminator feature-space is also minimized between the generated images and the training data. The additional losses enable the generator to learn subtle background details, resulting in a more realistic complex scene generation. During testing, a novel back-propagation based algorithm is used to generate images with statistics similar to the test images. More appropriate random noise samples are searched by directly minimizing the loss function between the test and generated images both in the image and discriminator feature-spaces. The network is not updated in this step; only the input noise samples are iteratively modified to minimize the loss function. Moreover, motion information is used to ensure that this loss is only computed on small-motion pixels. A novel dataset containing outdoor time-lapsed images from dawn to dusk with a full illumination variation cycle is also proposed to better compare the MOD algorithms in outdoor scenes. Accordingly, extensive experiments on five benchmark datasets and comparison with 30 existing methods demonstrate the strength of the proposed algorithm.

Performance characterization of (Pt,Au,Pd)/ZnO/n-Si/Al Schottky structures for varied temperature and UV illumination conditions

Abstract Herein this paper, morphological, electrical and optical (UV) characteristics are explored for ZnO/n-Si based different contact material Schottky heterojunctions through simulations and fabrication. The electron major ZnO crystalline thin films were deposited using RF-sputtering technique on n-type Si wafers. The structural and morphological properties of sputtered ZnO thin film was studied through tapping mode atomic force microscopy (AFM), and scanning electron microscopy (SEM). The electrical characterization of fabricated Schottky structures involved measuring of current-voltage characteristics for different temperatures ranging from 300 K to 400 K. Capacitance-voltage characteristics for fabricated Schottky heterojunctions were measured to estimate barrier height ( φ B ). The effect of temperature on ideality factor (η) and series resistance was also studied for Pd, Au and Pt Schottky heterojunctions. Increasing the lattice temperature from 300 K to 400 K led to gradual decrease in η and series resistance. Pt–ZnO shows the best Schottky behavior with experimental values of rectification ratio of 3.95 × 10 3 followed by 2.25 × 10 2 and 1.5 × 10 2 for Au and Pd respectively at V anode = ± 5 V . The current characteristics of fabricated Schottky structures were studied using 365 nm wavelength UV illumination source for observing detectivity (D) and responsivity (R). Best responsivity and D values were obtained for Pt/ZnO/Si and found to be 0.32 A / W and 4.12 × 10 9 mHz 1 2 / W followed by Au, and Pd. Pt based Schottky structure shows the fastest response to 365 nm UV light illumination with response time ( t r ) of 25 ms and recovery time ( t d ) of 48 ms The obtained values for figure of merits favor the idea of using Schottky junctions for optoelectronic applications.

Integration of remote sensing, gravity and geochemical data for exploration of Cu-mineralization in Alwar basin, Rajasthan, India

In spite of the dominance of traditional mineral exploration methods that demand physical characterization of rocks and intense field work, remote sensing technologies have also evolved in the recent past to facilitate mineral exploration. In the present study, we have processed visible near infrared (VNIR) and shortwave infrared (SWIR) bands of Advanced space-borne thermal emission and reflection radiometer (ASTER) data to detect surface mineralization signatures in Mundiyawas - Khera area in Alwar basin, north-eastern Rajasthan, India using spectral angle mapper (SAM). The potential of SAM method to detect target under variable illumination condition was used to delineate galena, chalcopyrite, malachite etc. as surface signatures of mineralization. It was ensured that the identified surface anomalies were spectrally pure using pixel purity index. Spectral anomalies were validated in the field and also using X-Ray diffraction data. Spectral anomaly maps thus derived were integrated using weight of evidence method with the lineament density, geochemical anomaly, bouger anomaly maps to identify few additional potential areas of mineralization. This study thus establishes the importance of remote sensing in mineral exploration to zero in on potentially ore rich but unexplored zones.

Development of a Simplified Radiometric Calibration Framework for Water-Based and Rapid Deployment Unmanned Aerial System (UAS) Operations

The current study sets out to develop an empirical line method (ELM) radiometric calibration framework for the reduction of atmospheric contributions in unmanned aerial systems (UAS) imagery and for the production of scaled remote sensing reflectance imagery. Using a MicaSense RedEdge camera flown on a custom-built octocopter, the research reported herein finds that atmospheric contributions have an important impact on UAS imagery. Data collected over the Lower Pearl River Estuary in Mississippi during five week-long missions covering a wide range of environmental conditions were used to develop and test an ELM radiometric calibration framework designed for the reduction of atmospheric contributions from UAS imagery in studies with limited site accessibility or data acquisition time constraints. The ELM radiometric calibration framework was developed specifically for water-based operations and the efficacy of using generalized study area calibration equations averaged across variable illumination and atmospheric conditions was assessed. The framework was effective in reducing atmospheric and other external contributions in UAS imagery. Unique to the proposed radiometric calibration framework is the radiance-to-reflectance conversion conducted externally from the calibration equations which allows for the normalization of illumination independent from the time of UAS image acquisition and from the time of calibration equation development. While image-by-image calibrations are still preferred for high accuracy applications, this paper provides an ELM radiometric calibration framework that can be used as a time-effective calibration technique to reduce errors in UAS imagery in situations with limited site accessibility or data acquisition constraints.

A Robust Automated Vision Based Filamentous Steel Strip Crack Detection System Based on Neuron Model Segmentation

Crack detection has always been a dominant requirement for steel industries to ensure quality production and seamless infrastructure maintenance. However, application complexities and defect morphological differences make existing approaches confined. Steel-strip surface often undergoes scratch, crack and fatigue conditions during production. Manual crack detection schemes are no longer effective in current day complex environment. Amongst major steel strip crack detection approaches vision based techniques have found potential; Filamentous crack which is caused due to fatigue or strain is fine-grained and thin and hence highly difficult to be detected by classical morphology and static threshold based schemes. In the present work steel strip surface (filamentous) crack detection system has been developed which employs Varying-Morphological Segmentation (VMS) also called Neuron-Model Segmentation (NMS) in conjunction with local directive filtering and active contour propagation. The proposed method can be stated as an augmented variational framework that employs multi-directional filters for local crack-region identification followed by automated multi-directional region growing and iterative contour evolution which performs level set energy minimization to achieve accurate crack detection even under topological non-linearity and varying illumination conditions Simulation results with standard benchmark data has confirmed that the proposed method exhibits satisfactory performance for steel strip surface cracks.

A New Band Ratio Approach for Discriminating Calcite and Dolomite by ASTER Imagery in Arid and Semiarid Regions

In this article, a new approach is developed for discrimination of calcite (limestone) and dolomite (dolostone) by utilizing data of Advanced Spaceborne Thermal Emission and Reflection Radiometer (ASTER). The study area is located at the Zagros Mountains, SW Iran, in which outcrops of sedimentary carbonate rocks are abundant. The approach exploits short-wave infrared spectral features of dolomite and calcite and is based on the spectral variations of these minerals in bands 7 and 8 of ASTER imagery. In order to evaluate the efficacy of the method, spectral analysis was carried out on the spectra of dolomite, dolostone, calcite, and limestone, available in ASTER spectral library. The statistical analysis of the spectra showed that dolomite and calcite have distinguishable b8/b7 band ratios. Spectral measurements of rock samples and knowledge of the mineral composition of rock samples attained by staining carbonate rocks in Alizarin red-S solution were used to evaluate the method used in this study. The applied imagery was normalized by the internal average relative reflectance (IARR) method due to the arid and semiarid climate of the region. The results showed that combined with spectral measurements of rock samples, the ((b5 + b9)/b7)/((b6 + b9)/b8), and b8/b7 band ratios can be used to effectively discriminate limestone and dolostone. This approach is completely independent of variations in illumination conditions of image pixels; therefore, topographic correction of the image is not needed. The approach performs better in areas where weathering of rock surfaces and vegetation cover are minimal.

Passion fruit detection and counting based on multiple scale faster R-CNN using RGB-D images

The accurate and reliable fruit detection in orchards is one of the most crucial tasks for supporting higher level agriculture tasks such as yield mapping and robotic harvesting. However, detecting and counting small fruit is a very challenging task under variable lighting conditions, low-resolutions and heavy occlusion by neighboring fruits or foliage. To robustly detect small fruits, an improved method is proposed based on multiple scale faster region-based convolutional neural networks (MS-FRCNN) approach using the color and depth images acquired with an RGB-D camera. The architecture of MS-FRCNN is improved to detect lower-level features by incorporating feature maps from shallower convolution feature maps for regions of interest (ROI) pooling. The detection framework consists of three phases. Firstly, multiple scale feature extractors are used to extract low and high features from RGB and depth images respectively. Then, RGB-detector and depth-detector are trained separately using MS-FRCNN. Finally, late fusion methods are explored for combining the RGB and depth detector. The detection framework was demonstrated and evaluated on two datasets that include passion fruit images under variable illumination conditions and occlusion. Compared with the faster R-CNN detector of RGB-D images, the recall, the precision and F1-score of MS-FRCNN method increased from 0.922 to 0.962, 0.850 to 0.931 and 0.885 to 0.946, respectively. Furthermore, the MS-FRCNN method effectively improves small passion fruit detection by achieving 0.909 of the F1 score. It is concluded that the detector based on MS-FRCNN can be applied practically in the actual orchard environment.

System Integration of Sensor-Fusion Localization Tasks Using Vision-Based Driving Lane Detection and Road-Marker Recognition

This article proposes a vision-based perception system of using a monocular camera to detect the high-level features in the form of road markers and driving lanes for providing reliable visual measurements. Road markers and driving lanes are chosen because of their visually distinctive appearance compared to other objects as well as being easily annotated in the predefined digital map. For road-marker recognition, a template-matching-based method is applied to recognize the marker type and to estimate the corresponding position and orientation as well. For driving-lane detection, the proposed gradient orientation consistency combining the inverse perspective mapping spatial constraints is used to initialize the clearly visible lanes in the initial detection. Finally, the well-known particle filter is employed to integrate the visual information, inertial measurement unit (IMU), and global position system (GPS) data complementarily for correcting GPS errors. In particular, the lane measurement and road-marker measurement provide the lateral offset and relative position information, respectively, with respect to the ego vehicle. The IMU is used to estimate the dynamic behavior of the ego vehicle. The proposed vehicle localization system is evaluated in the real driving scenario of the standard campus environment within varying illumination conditions. The experiment results show that the lane-level localization accuracy is achieved by detecting road markers and driving lanes robustly.

Face Recognition for Varying Illumination and Different Optical Zoom Using a Combination of Binary and Geometric Features

Preservation of image features caused by binary conversion is a difficult task under variation of illumination conditions. Several binary conversion-based methods have used an adaptive thresholding technique to improve their performance under illumination variation conditions because of its robustness. However, the performances of existing methods were still limited under high differences illumination conditions especially for uncontrolled lighting sources. In addition, various length of face-to-camera distance gives significant problem affect for the performance of face recognition method. It happens when various images are available for the same person with different length face-to-camera distances due to the appearance of varying facial features of the same person. Therefore, this study proposed to combine the strength normalization and feature-based method to build an illumination distribution model to overcome this problem. With the proposed method the illumination model will fit with variation of illumination conditions in a whole image to generate an adaptive threshold for a novel columnar binary conversion method. The proposed method consists of five main stages, starting with eye area detection using the developed Viola–Jones algorithm. Next, the iris is detected using the Circular Hough Transform (CHT) method and will convert it into binary using the proposed Columnar Binary Conversion (CBC) method to preserve the appearance of the facial features under the illumination variation. Then, the proposed Facial Feature Region Normalization (FFRN) method is performed to improve the effects of different optical zooms for the classification step. The classification is conducted based on the similarity measurement between the extracted normalised binary face region and the dataset that must be converted into their equivalent normalised binary images. The proposed method is evaluated on two different smartphone databases, namely as Smartphone Face Video (SFV) and MOBIO. The performance results showed the outperformance of the proposed method.

Superpixel-based segmentation algorithm for mature citrus

With the decrease of agricultural labors and the increase in production costs, harvesting robots have become a research hotspot in recent years. To guide harvesting robots to pick mature citrus more precisely under variable illumination conditions, an image segmentation algorithm based on superpixel was proposed. Efficient simple linear iterative clustering (SLIC) algorithm which takes similarity of adjacent pixels into account was adopted to segment the images captured under variable illumination conditions into superpixels. The color and texture features of these superpixels were extracted and fused into feature vectors as descriptors to train backpropagation neural networks (BPNN) classifier in the next step. The adjacency information of superpixels was considered by calculating the global-local binary pattern (LBP) in R component images when extracting texture features. To accelerate the classification process, the mean of Cr-Cb image was utilized to find superpixels of interest which were regarded as candidates of citrus superpixels. These candidates were then classified by a pre-trained BPNN model with superpixel-level accuracy of 98.77% and pixel-level accuracy of 94.96%, while the average time to segment one image was 0.4778 s. Therefore, the results indicated that a superpixel-based segmentation algorithm toward citrus images had decent light robustness as well as high accuracy that could guide harvesting robot to pick mature citrus efficiently. Keywords: superpixel, image segmentation, BPNN, variable illumination, mature citrus DOI: 10.25165/j.ijabe.20201304.5607 Citation: Yang Q H, Chen Y Q, Xun Y, Bao G J. Superpixel-based segmentation algorithm for mature citrus. Int J Agric & Biol Eng, 2020; 13(4): 166–171.

Face Recognition Using the Combination of Weighted Sparse Representation-based Classification and Singular Value Decomposition Face

Given the increasing need for the creation and development of automated systems, the problem of detecting and identifying the faces of people in the images has been considered by the researchers. In recent years, the sparse representation based classification has been of great interest to researchers. The goal of this investigation is to provide a quick and effective way to identify faces based on the sparse representation. Since the basis of sparse representation is to calculate it through L1-norm optimization for high dimensional dictionary with high computational volume, a smoothed L0-norm optimization-based method was introduced. At the time of obtaining the sparse representation using smoothed L0-norm, due to the high degree of redundancy, when the number of facial features is low, the conditions for the unique sparse representation are not properly satisfied or the model is not accurate, the risk of getting stuck in the local minima will be so much. Hence, the idea of the weighted sparse representation to narrow the search space is presented. In addition, to enhance the identification accuracy in face recognition and face verification under varying illumination conditions, the Singular Value Decomposition method can be used in the feature extraction step. In the extraction stage, the normalized coefficients of Singular Value Decomposition are not sensitive to different lightness conditions, resulting to reduce the effect of illumination variation on the normalized images. Compared to earlier methods, which often fail even in the event of a slight turbulence, this technique can successfully produce facial structural information while preventing the effect of different lightnesses such as cast shadows. The simulation results on the Extended Yale B database show that the proposed method has high accuracy in face recognition with less computational volume and higher speed than the L1-norm based approach.

Highly Robust and Automated Vision based Filamentous Steel Strip Crack Detection System

Crack detection has always been a dominant requirement for steel industries to ensure quality production and seamless infrastructure maintenance. However, application complexities and defect morphological differences make existing approaches confined. Steel-strip surface often undergoes scratch, crack and fatigue conditions during production. Manual crack detection schemes are no longer effective in current day complex environment. Amongst major steel strip crack detection approaches vision based techniques have found potential; Filamentous crack which is caused due to fatigue or strain is fine-grained and thin and hence highly difficult to be detected by classical morphology and static threshold based schemes. In the present work steel strip surface (filamentous) crack detection system is developed which employs Varying-Morphological Segmentation (VMS) also called Neuron-Model Segmentation (NMS) in conjunction with local directive filtering and active contour propagation. The proposed method can be stated as an augmented vibrational framework that employs multi-directional filters for local crack-region identification followed by automated multi-directional region growing and iterative contour evolution which performs level set energy minimization to achieve accurate crack detection even under topological non-linearity and varying illumination conditions Simulation results with standard benchmark data has confirmed that the proposed method exhibits satisfactory performance for steel strip surface cracks.

Canonical Illumination Decomposition and Its Applications

Raw data acquired by imaging devices are converted into digital images by post-processing algorithms. However, these algorithms are significantly affected by numerous illumination conditions. Particularly, in the case in which illumination conditions depend on canonical light sources, unwanted light sources that locally illuminate the scene or mixed light from several light sources are recognized as the spatially varying illumination conditions. These complex illumination conditions cause several artifacts by affecting the digital image acquisition process. For example, optical aberrations are generated by refraction of complex light, or illumination estimation is significantly affected by the different color temperatures of multiple light sources. To overcome these problems, this study proposes an algorithm that decomposes the complex illumination from several light sources. First, the spatially varying illumination condition is discussed, and the artifacts generated by the conditions, such as false colors and aberrations, are analyzed. Second, mixed light from several canonical light sources is decomposed based on the imaging devices and spectral information of the canonical light sources. The proposed method has low complexity and increased applicability. Furthermore, the improvement scheme based on the proposed method has a parallelized structure and can be easily applied to various types of algorithms, such as color constancy, deconvolution, denoising, and contrast enhancement. The algorithms employing the improvement scheme show the potential of the proposed method for solving the problems associated with multiple light sources.

Color Calibration of Proximal Sensing RGB Images of Oilseed Rape Canopy via Deep Learning Combined with K-Means Algorithm

Plant color is a key feature for estimating parameters of the plant grown under different conditions using remote sensing images. In this case, the variation in plant color should be only due to the influence of the growing conditions and not due to external confounding factors like a light source. Hence, the impact of the light source in plant color should be alleviated using color calibration algorithms. This study aims to develop an efficient, robust, and cutting-edge approach for automatic color calibration of three-band (red green blue: RGB) images. Specifically, we combined the k-means model and deep learning for accurate color calibration matrix (CCM) estimation. A dataset of 3150 RGB images for oilseed rape was collected by a proximal sensing technique under varying illumination conditions and used to train, validate, and test our proposed framework. Firstly, we manually derived CCMs by mapping RGB color values of each patch of a color chart obtained in an image to standard RGB (sRGB) color values of that chart. Secondly, we grouped the images into clusters according to the CCM assigned to each image using the unsupervised k-means algorithm. Thirdly, the images with the new cluster labels were used to train and validate the deep learning convolutional neural network (CNN) algorithm for an automatic CCM estimation. Finally, the estimated CCM was applied to the input image to obtain an image with a calibrated color. The performance of our model for estimating CCM was evaluated using the Euclidean distance between the standard and the estimated color values of the test dataset. The experimental results showed that our deep learning framework can efficiently extract useful low-level features for discriminating images with inconsistent colors and achieved overall training and validation accuracies of 98.00% and 98.53%, respectively. Further, the final CCM provided an average Euclidean distance of 16.23 ΔΕ and outperformed the previously reported methods. This proposed technique can be used in real-time plant phenotyping at multiscale levels.

An Intelligent Speed Limit Sign Recognition Approach Towards an Embedded Driver Assistance System

Road traffic safety has become a significant global public health issue. The number of traffic crashes is increasing in alarming proportions, leading to a large number of deaths and injuries. Most road accidents occur due to human errors including exceeding speed limit and failure to abide by driving rules. Therefore, in order to solve this issue, advanced driver-assistance systems are more and more in use thanks to their capabilities in minimizing the human error. These systems are used to enhance or adapt some or all of the tasks involved in operating a vehicle. Designers rely heavily on Artificial Intelligence in order to operate these systems. In this framework, this paper discusses the development of an intelligent speed limit signs’ recognition system, which can substantially enhance road safety. Since this system is conceived to be implanted on an FPGA card, the main challenges consist in achieving a high recognition rate with a low complexity level in the proposed algorithm. This will undoubtedly lead up to an optimized hardware architecture suitable for real time processing. For this purpose, a two-step based vision speed limit signs’ detection and recognition system has been proposed. The first step concerns sign candidate’s detection based on color and shape analysis; it consists in different sub image processing levels. The second step deals with the recognition and identification of the detected signs. To this end, several Machine Learning algorithms and several architectures of multilayer Neural Network and Wavelet Neural Network have been evaluated. The analysis of performance results and comparison with other widely used techniques have shown the effectiveness and efficiency of the proposed technique in terms of percentage of correct classification and execution time even for images captured under varied orientations and varied illumination conditions.