Foliage Environment Research Articles

Design and Control of Autonomous Rover for Foliage Navigation

Implementation of UGV in civilian applications is getting trendy and normalized due to its solid achievement in executing mission under harsh environments. The UGV foliage environment-oriented applications even attracted the people’s attention in correspond sectors to ease their tasks with guaranteed performance. Given this, the development of the autonomous rover from sensors and control aspects with the consideration of foliage environment interest people to enhance its functionality. To ensure the sensor is not easily affected by the environment factor, the radar and the camera are selected to provide the environment perception to the rover. The approach for a linear Proportional-Derivative (PD) controller with the dynamic modelling of the UGV is also discussed in this paper. The study shows preliminary results that are working.

To Develop a Model for 4g LTE and Predictable 5G at 3500 Mhz that Would Predict the Path Loss for the Environment in Semi-Urban or Mixture of Urban and Rural Surroundings at Specific Geographical Locations

Abstract: In wireless communication, a planned network is given by the path loss model. Link budgeting, coverage prediction, and system performance optimization are indispensable in developing an accurate, simple, and general path loss model. To predict path loss in a particular environment each type of path loss propagation model is designed, it may be inaccurate in another different environment. In this paper, we are trying to predict a path loss model of Durgapur considering a particular place with a mixture of high-rise buildings, sub-urban, open, and foliage environments. For this proposal, the model area has been divided into twelve sectors taking 30° sectoring of radii 5 km and applying the path loss model for the calculation of path loss. Index Terms: Path loss, Predicted model, Outdoor propagation model consideration, Cell site selection, results, and discussions.

Pixelwise instance segmentation of leaves in dense foliage

• Pixelwise Instance segmentation of leaves is performed on mixes of plant species. • A new shape-based loss function is proposed and applied to each connected component. • The segmentation output is refined using a Watershed and a DeepIndices approach. • A benchmark of the method is performed on “leaf segmentation challenges”. • A new multi-spectral dataset of 300 images acquired in natural light is shared. Detecting and identifying plants using image analysis is a key step for many applications in precision agriculture (from phenotyping to site specific weed management). Instance segmentation is usually carried on to detect entire plants. However, the shape of the detected objects changes between individuals and growth stages. A relevant approach to reduce these variations is to narrow the detection on the leaf. Nevertheless, segmenting leaves is a difficult task, when images contain mixes of plant species, and when individuals overlap, particularly in an uncontrolled outdoor environment. To leverage this issue, this study based on recent Convolutional Neural Network mechanisms, proposes a pixelwise instance segmentation to detect leaves in dense foliage environment. It combines “deep contour aware” (to separate the inner of big leaves from its edges), “Leaf Segmentation trough classification of edges” (to separate instances with a specific inner edges) and “Pyramid CNN for Dense Leaves” (to consider edges at different scales). But the segmentation output is also refined using a Watershed and a method to compute optimized vegetation indices (DeepIndices). The method is compared to others running the leaf segmentation challenge (provided by the International Network on Plant Phenotyping) and applied on an external dataset of Komatsuna plants. In addition, a new multispectral dataset of 300 images of bean plants is introduced (with dense foliage, individuals overlapping, mixes of species and natural lighting conditions). The ground truth (e.g. the leaves boundaries) is defined by labelled polygons and can be used to train and assess the performance of various algorithms dedicated to leaf detection or crop/weed classification. On the usual datasets, the performances of the proposed method are similar to those of the usual methods involved in the leaf segmentation challenges. On the new dataset, their results are strongly better than those of the usual RCNN method. Remaining errors are bad fusion between neighboring areas and over segmentation of multi-foliate leaves. Structural analysis methods could be studied in order to overcome these deficiencies.

A Climate Adaptation Device-Free Sensing Approach for Target Recognition in Foliage Environments

Accurate and efficient foliage penetration (FOPEN) target recognition plays a vital role in many mission-critical applications, ranging from civilian to surveillance and military. Recently, device-free sensing (DFS), as an emerging technique, has gained great popularity because it requires no dedicated equipment other than wireless transceivers. Although some DFS-based approaches have been successfully applied in foliage environments, they are vulnerable to climate dynamics and heavily rely on re-labeling large amounts of new data when the weather is altered. To address this issue, a CNN-based weather adaptive target recognition network (WATRNet) is proposed in this paper. Specifically, a lightweight weather conditional normalization (WCN) module is embedded atop each convolutional block to encode inputs under different weather conditions into a shared latent feature space. Under an end-to-end learning manner, the proposed WATRNet first learns knowledge from sufficient labeled data under a certain weather condition to achieve a precise classifier. When applying this model under another weather condition, only the WCN module needs to be retrained using limited new labeled samples to learn weather-invariant features, while the rest convolutional parameters in WATRNet are frozen. Consequently, the domain discrepancy caused by climate variations can be adaptively mitigated with as few relabeled data as possible. Comprehensive evaluations are carried out on a real FOPEN dataset collected under four different weather conditions. Experimental results verify that the presented method can achieve over 90% accuracy, even when it implements from a normal weather condition to another severe weather condition with only small amounts of training samples.

Semantic VPS for Smartphone Localization in Challenging Urban Environments.

Accurate smartphone-based outdoor localization systems in deep urban canyons are increasingly needed for various IoT applications. As smart cities have developed, building information modeling (BIM) has become widely available. This article, for the first time, presents a semantic Visual Positioning System (VPS) for accurate and robust position estimation in urban canyons where the global navigation satellite system (GNSS) tends to fail. In the offline stage, a material segmented BIM is used to generate segmented images. In the online stage, an image is taken with a smartphone camera that provides textual information about the surrounding environment. The approach utilizes computer vision algorithms to segment between the different types of material class identified in the smartphone image. A semantic VPS method is then used to match the segmented generated images with the segmented smartphone image. Each generated image contains position information in terms of latitude, longitude, altitude, yaw, pitch, and roll. The candidate with the maximum likelihood is regarded as the precise position of the user. The positioning result achieved an accuracy of 2.0 m among high-rise buildings on a street, 5.5 m in a dense foliage environment, and 15.7 m in an alleyway. This represents an improvement in positioning of 45% compared to the current state-of-the-art method. The estimation of yaw achieved accuracy of 2.3°, an eight-fold improvement compared to the smartphone IMU.

Deep factor analysis for weather varied sense-through-foliage target detection

In this paper, the influence of seasonal variation on target detection accuracy and the effectiveness of deep factor analysis (DFA) in signal denoising are studied. To extensively verify the universality of the DFA_based approach, a variety of target objects, including no target, human, wood board and iron cabinet targets, are measured in foliage environment under four different weather conditions. Then, after removing background noise from the collected data, deep factor analysis is carried out to reduce the impact of noise. The experimental results show that the influence of weather variation on target detection can be effectively eliminated by DFA_based algorithm, which can improve the average classification accuracy in all seasons. Finally, by means of cross validation, the effectiveness of DFA_based algorithm on signal denoising and the influence on target detection accuracy are further studied. The method is stable and universal in any weather conditions, even in hazy and snowy days, which can be stable at about 93%.

Low data regimes in extreme climates: Foliage penetration personnel detection using a wireless network-based device-free sensing approach

As far as low-cost deployment is concerned, wireless network-based device-free sensing (DFS) is of great interest and has successfully demonstrated the feasibility in Foliage penetration (FOPEN) target recognition. The classification accuracy of this technology is known to dramatically decrease in extreme climates where the received signals tend to be severely attenuated; while deep learning approaches have boosted performance, they only perform effectively when trained with large amounts of labeled data. Consequently, it is still unknown how to ensure reasonable detection accuracy in extreme climates where sufficient samples are difficult to obtain. To address this concern, we adopt two special measures for performance enhancement in this paper. One measure is to employ higher-order spectral (HOS) analysis to transform the time-domain signals into the bispectrum image representations, so that the shift to an image classification task could provide the advantage of using the existing Convolutional Neural Network (CNN) models. More importantly, the immunity of the approach against the unwanted clutters in foliage environments can be improved. The other one is to present an end-to-end Deep Learning Data Augmentation and Classification (DLDAC) model comprised of a Deep Convolutional Generative Adversarial Network (for data augmentation) and a SqueezeNet CNN backbone (for target classification), which can improve the classifier performance by using the augmented data on-the-fly. Thus, the negative impacts of low data regimes in extreme climates can be considerably accommodated. To evaluate the effectiveness of the proposed approach, comprehensive experiments are conducted on a real FOPEN dataset collected by impulse-radio ultra-wideband (IR-UWB) transceivers under three severe weather conditions. The experimental results demonstrate that even when only 300 training samples are taken for each type of target under every weather condition, the average classification accuracy of the proposed approach is still better than 92% in terms of distinguishing between human and other targets.

Imaging of Human Walking Behind the Obstacle Utilizing Pulsed Radar Technique in the C-Band for Military Surveillance Applications

This paper presents the applied pulsed radar signal processing which works in the C-band for imaging of walking human responses behind the wooden wall and foliage environment for military monitoring applications. The overall scenario of this work has been theoretically modelled to provide an insight into the interaction between the pulsed radar system and the surrounding environment. The experiment of this work has been performed under the (1) wooden wall and (2) foliage environment for the purpose of a preliminary study. Considering that there have been many types of research have been done utilizing UWB with a lower center frequency, this work mainly focuses on proposing a series of the pulsed radar signal processing worked in unique C-band for extracting the walking human response from other reflections associated with clutters. The three-dimensional images of walking human have been finally reconstructed in 20 dB scale under the wooden wall and foliage environment.

Cost-Effective Foliage Penetration Human Detection Under Severe Weather Conditions Based on Auto-Encoder/Decoder Neural Network

Military surveillance events and rescue activities are vital missions for the Internet-of-Things. To this end, foliage penetration for human detection plays an important role. However, although the feasibility of that mission has been validated, we observe that it still cannot perform promisingly under severe weather conditions, such as rainy, foggy, and snowy days. Therefore, in this paper, experiments are conducted under severe weather conditions based on a proposed deep learning approach. We present an auto-encoder/decoder (Auto-ED) deep neural network that can learn the deep representation and conduct classification task concurrently. Since the property of cost-effective, the device-free sensing techniques are used to address human detection in our case. As we pursue the signal-based mission, two components are involved in the proposed Auto-ED approach. First, an encoder is utilized that encode signal-based inputs into higher dimensional tensors by fractionally strided convolution operations. Then, a decoder is leveraged with convolution operations to extract deep representations and learn the classifier simultaneously. To verify the effectiveness of the proposed approach, we compare it with several machine learning approaches under different weather conditions. Also, a simulation experiment is conducted by adding additive white Gaussian noise to the original target signals with different signal to noise ratios. Experimental results demonstrate that the proposed approach can best tackle the challenge of human detection under severe weather conditions in the high-clutter foliage environment, which indicates its potential application values in the near future.

Comprehensive measurement and modeling in foliage environments using UHF UWB ground-based radar

The precise knowledge of the statistical properties of clutter plays a key role in radar target detection in foliage environments. Owing to a wealth of multiple scattering, the selection of an appropriate model for diverse foliage environments remains a conundrum. Thus the statistical modeling of the foliage clutter in different environments is focused on in this paper. In particular, the primary contribution is to characterize and parameterize the amplitude of the foliage clutter in three typical foliage environments of different densities, including line-of-sight (LOS) forest environment, non line-of-sight (NLOS) forest-penetration environment, and NLOS bush-penetration environment. Based on the real clutter data acquired with an ultra-high frequency (UHF) ultra-wideband (UWB) ground-based radar, the experimental results show that the specific foliage type and configuration has a significant impact on the distribution of foliage clutter. Furthermore, by means of Kullback–Leibler distance (KLD), log-logistic, and distributions with estimated parameters are demonstrated to be the best choice to model the clutter in the LOS forest environment, NLOS forest-penetration environment and NLOS bush-penetration environment, respectively. The proposed models are great advantages on understanding and prediction of the clutter in foliage environments.

Polarized Light Compass-Aided Visual-Inertial Navigation Under Foliage Environment

This paper presents a method to extract heading information from the sky light polarization pattern and successfully implements the polarized light compass (PL-compass) under foliage environment with heavy occlusions for the first time. A classifier based on the primal support vector machine is trained to detect the sky area, and the random sample consensus algorithm is used to choose the inliers among the sky area. The sun vector is built upon the valid measurements. The attitude angles (Roll and Pitch) from the inertial navigation system (INS) are used to establish the Zenith direction when the platform tilts during traveling. The results show that the PL-compass can provide accurate heading angle (RMSE = 1.58°) by seeing only a tiny part of the skylight (minimum of 0.028%) in the dynamic vehicle test. The PL-compass is also integrated with the visual INS based on the indirect extended Kalman filter to improve the navigation accuracy. Each time a new measurement becomes available, the states estimated by the INS are used to check the consistency of the innovation and reject the outliers. The results show that the position errors of the integrated navigation system are greatly reduced with the help of the PL-compass. The estimated trajectory tracks the ground truth very well. The position error is 25.9 m (1.03% of the distance traveled) with heading errors less than 1° in the experiment.

Device-Free Sensing for Personnel Detection in a Foliage Environment

In this letter, the possibility of using device-free sensing (DFS) technology for personnel detection in a foliage environment is investigated. Although the conventional algorithm that based on statistical properties of the received-signal strength (RSS) for target detection at indoor or open-field environment has come a long way in recent years, it is still questionable if this algorithm is fully functional at outdoor with the changing atmosphere and ground conditions, such as a foliage environment. To answer this question, a variety of the measured data have been taken using different targets in a foliage environment. Applying these data along with support vector machine, the impact on detection accuracy due to different classification algorithms is studied. An algorithm that based on the extraction of the high-order cumulant (HOC) of the signals is presented, while the conventional RSS-based one is used as a benchmark. The measurement results show that the classification accuracy of the HOC-based algorithm is better than the RSS-based one by at least 17%. Moreover, to ensure the reliability of the HOC-based approach, the impact on classification accuracy due to different numbers of training samples and different values of signal-to-noise ratio is extensively verified using experimentally recorded samples. To the best of our knowledge, this is the first time that a DFS-based sensing approach is demonstrated to have a potential to distinguish between human and small-animal targets in a foliage environment.

Enhanced GNSS Signal Tracking in Fading Environments using Frequency Diversity

A new methodology to enhance the GNSS parameter estimation accuracy in multipath fading environments using the frequency diversity reception is proposed herein. In such environments, fading occurrences observed in different frequency bands are independent of each other. Characteristics of frequency diversity reception using GPS L1 and L2C signals in dense fading conditions are first discussed and compared with those of spatial diversity reception. Comparative analyses of characterization metrics between frequency diversity and spatial diversity signals support the argument that the former is as effective as the latter. A frequency diversity based combined tracking approach is then proposed, and the performance is evaluated using the data collected in dense foliage and residential environments. Results show that frequency diversity based combined tracking results in improved performance compared to that of single frequency tracking. 3D position error reduction achieved by the proposed method is 52% in foliage conditions and 50% in residential environments. Copyright © 2017 Institute of Navigation

Autonomous Navigation of UAV in Foliage Environment

This paper presents a navigation system that enables small-scale unmanned aerial vehicles to navigate autonomously using a 2D laser range finder in foliage environment without GPS. The navigation f...

A method of obstacle identification in ultra wideband wireless sensor networks

Obstacle identification is a difficult task, which is more challenged in foliage environment. In this paper, a method of target detection is proposed, which attempts to extract information from the data being transmitted around the wireless sensor network (WSN) to identify targets that might be within the local, foliage obscured scene. The selected bispectra algorithm is applied to extract the feature vector, as well as radial–basis function (RBF) neural network is used to realise the obstacle classification. According to the experiment results, this method is able to identify the existence and the different distances of the obstacles measured in outdoor foliage scene with a good recognition rate.

Target identification in foliage environment using UWB radar with hybrid wavelet–ICA and SVM method

This paper proposes a method of target identification in foliage environment, specifically to identify the number of people present in foliage environment. This method is based on the ultra-wideband (UWB) radar sensor networks (RSNs) model. UWB technology can be used for target identification and intrusion detection, we can integrate UWB-IR technology and passive radar theory directly into target detection and identification in the foliage environment through analyzing and processing of the received UWB signal. Firstly, extensive Wideband Impulse Radio (UWB-IR) was sent and received within RSNs in foliage environment. Subsequently, we used hybrid Wavelet Analysis (WA) and Independent Component Analysis (ICA) method to extract features that can reflect the scenario characteristic. Finally, those extracted features are used to train Support Vector Machine (SVM) and to classify the number of people in foliage environment. The result with an average identification rate of no less than 95% shows the effectiveness of the proposed method.

New method for target identification in a foliage environment using selected bispectra and chaos particle swarm optimisation‐based support vector machine

In this study, a novel method for target identification in a foliage environment is presented. This method is based on the ultra wideband (UWB) wireless sensor networks (WSNs) model, and the foliage environment is specially considered. The data used to identify the targets are derived from the received signal waveform, so most existing transceivers can be exploited as detecting sensors, which leads to a potential low-cost way to identify targets during the normal communications within the WSNs under foliage environment. The selected bispectra algorithm is applied to extract the feature vector, and chaos particle swarm optimisation-based support vector machine is used as the target classifier. Experiments with real-world data samples indicate that this method has an excellent classification performance in a foliage environment. Moreover, this method shows potential for online training.

Radar sensor network for target detection using Chernoff information and relative entropy

In this paper, we propose to apply information theory to Ultra wide band (UWB) radar sensor network (RSN) to detect target in foliage environment. Information theoretic algorithms such as Maximum entropy method (MEM) and mutual information are proven methods, that can be applied to data collected by various sensors. However, the complexity of the environment poses uncertainty in fusion center. Chernoff information provides the best error exponent of detection in Bayesian environment. In this paper, we consider the target detection as binary hypothesis testing and use Chernoff information as sensor selection criterion, which significantly reduces the processing load. Another strong information theoretic algorithm, method of types, is applicable to our MEM based target detection algorithm as entropy is dependent on the empirical distribution only. Method of types analyzes the probability of a sequence based on empirical distribution. Based on this, we can find the bound on probability of detection. We also propose to use Relative entropy based processing in the fusion center based on method of types and Chernoff Stein Lemma. We study the required quantization level and number of nodes in gaining the best error exponent. The performance of the algorithms were evaluated, based on real world data.

Diversity Antenna System for Satellite Digital Audio Radio

A diversity antenna system with antennas embedded in rear view mirrors of a vehicle is proposed for satellite digital audio radio system. Antenna diversity is needed because hidden antennas exhibit limited capability and composite body vehicles have poor reception due to no ground plane availability. Pattern gain diversity achieved with the proposed system is proven with on-vehicle antenna simulations and gain measurements. Selection combining diversity receiver architecture is also proposed and the system is tested in real time under two fading scenarios: weak satellite signal in dense foliage and multipath terrestrial environment with frequent satellite blockages. In both cases, the diversity system outperformed the reference antenna system with less mutes times (0.6% versus 0.8% in multipath, 0.1% versus 0.25% in dense foliage) and Reed-Solomon block errors (1.75% versus 2.18% in multipath, 0.87% versus 1.18% in dense foliage). The proposed rear-view mirror location is ideal for minimum signal degradation compared to windshield, backlite, and dashboard antenna installations.

Performance analysis of advanced GPS receiver technique in radio frequency difficult environment

Global Positioning System (GPS) is widely used in many applications, especially on its position, velocity and timing (PVT) services. In general, a GPS receiver performs accurately and smoothly under open-sky environment. However, under urban canyon and dense foliage environments, a GPS receiver could not provide PVT services adequately due to GPS signal blockage or multipath. As a result, this paper develops and implements an advance GPS receiver technique, the Vector Tracking (VT) technique, to compare its performance with the conventional standard GPS receiver design under radio frequency difficult environments. The VT technique is based on an Extended Kalman Filter (EKF) to track all GPS satellites simultaneously and to estimate the user's position, velocity, and clock bias. The VT technique takes the advantage of the user's dynamic to predict the associated changes in the GPS signal, and it could thus facilitate the GPS receiver to bridge the temporary signal outages. Additionally, the tuning of the EKF is the key performance factor of the VT technique, and two algorithms to estimate the noise covariance, namely the correlation method and the empirical setting method, are discussed in this paper as well. Finally, this paper presents the performance gained from the developed VT technique in comparison to the conventional GPS receiver under various Radio Frequency (RF) difficult environments.