Attribute Feature Perturbation-Based Augmentation of SAR Target Data.

Large-scale, diverse, and high-quality data are the basis and key to achieving a good generalization of target detection and recognition algorithms based on deep learning. However, the existing methods for the intelligent augmentation of synthetic aperture radar (SAR) images are confronted with several issues, including training instability, inferior image quality, lack of physical interpretability, etc. To solve the above problems, this paper proposes a feature-level SAR target-data augmentation method. First, an enhanced capsule neural network (CapsNet) is proposed and employed for feature extraction, decoupling the attribute information of input data. Moreover, an attention mechanism-based attribute decoupling framework is used, which is beneficial for achieving a more effective representation of features. After that, the decoupled attribute feature, including amplitude, elevation angle, azimuth angle, and shape, can be perturbed to increase the diversity of features. On this basis, the augmentation of SAR target images is realized by reconstructing the perturbed features. In contrast to the augmentation methods using random noise as input, the proposed method realizes the mapping from the input of known distribution to the change in unknown distribution. This mapping method reduces the correlation distance between the input signal and the augmented data, therefore diminishing the demand for training data. In addition, we combine pixel loss and perceptual loss in the reconstruction process, which improves the quality of the augmented SAR data. The evaluation of the real and augmented images is conducted using four assessment metrics. The images generated by this method achieve a peak signal-to-noise ratio (PSNR) of 21.6845, radiometric resolution (RL) of 3.7114, and dynamic range (DR) of 24.0654. The experimental results demonstrate the superior performance of the proposed method.

Dispersion analysis of the 2017 Persian Gulf oil spill based on remote sensing data and numerical modelling.

Oil spills, detected by SAR sensors as dark areas, are highly effective marine pollutants that affect the ocean surface. These spills change the water surface tension, attenuating capillary gravitational waves and causing specular reflections. We conducted a case study in the Persian Gulf (Arabian Sea to the Strait of Hormuz), where approximately 163,900 gal of crude oil spilled in March 2017. Our study examined the relationship between oil weathering processes and extracted backscatter values using zonal slices projected over SAR-detected oil spills. Internal backscatter values ranged from -22.5 to -23.5, indicating an oil chemical binding and minimal interaction with seawater. MEDSLIK-II simulations indicated increased oil solubilization and radar attenuation rates with wind, facilitating coastal dispersion. Higher backscatter at the spill edges compared to the core reflected different stages of oil weathering. These results highlight the complex dynamics of oil spills and their environmental impact on marine ecosystems.

A SAR Ship Detection Method Based on Adversarial Training.

SAR (synthetic aperture radar) ship detection is a hot topic due to the breadth of its application. However, limited by the volume of the SAR image, the generalization ability of the detector is low, which makes it difficult to adapt to new scenes. Although many data augmentation methods-for example, clipping, pasting, and mixing-are used, the accuracy is improved little. In order to solve this problem, the adversarial training is used for data generation in this paper. Perturbation is added to the SAR image to generate new samples for training, and it can make the detector learn more abundant features and promote the robustness of the detector. By separating batch normalization between clean samples and disturbed images, the performance degradation on clean samples is avoided. By simultaneously perturbing and selecting large losses of classification and location, it can keep the detector adaptable to more confrontational samples. The optimization efficiency and results are improved through K-step average perturbation and one-step gradient descent. The experiments on different detectors show that the proposed method achieves 8%, 10%, and 17% AP (Average Precision) improvement on the SSDD, SAR-Ship-Dataset, and AIR-SARShip, compared to the traditional data augmentation methods.

Ship Detection in Synthetic Aperture Radar Images under Complex Geographical Environments, Based on Deep Learning and Morphological Networks.

Synthetic Aperture Radar (SAR) ship detection is applicable to various scenarios, such as maritime monitoring and navigational aids. However, the detection process is often prone to errors due to interferences from complex environmental factors like speckle noise, coastlines, and islands, which may result in false positives or missed detections. This article introduces a ship detection method for SAR images, which employs deep learning and morphological networks. Initially, adaptive preprocessing is carried out by a morphological network to enhance the edge features of ships and suppress background noise, thereby increasing detection accuracy. Subsequently, a coordinate channel attention module is integrated into the feature extraction network to improve the spatial awareness of the network toward ships, thus reducing the incidence of missed detections. Finally, a four-layer bidirectional feature pyramid network is designed, incorporating large-scale feature maps to capture detailed characteristics of ships, to enhance the detection capabilities of the network in complex geographic environments. Experiments were conducted using the publicly available SAR Ship Detection Dataset (SSDD) and High-Resolution SAR Image Dataset (HRSID). Compared with the baseline model YOLOX, the proposed method increased the recall by 3.11% and 0.22% for the SSDD and HRSID, respectively. Additionally, the mean Average Precision (mAP) improved by 0.7% and 0.36%, reaching 98.47% and 91.71% on these datasets. These results demonstrate the outstanding detection performance of our method.

SAR Image Registration: The Combination of Nonlinear Diffusion Filtering, Hessian Features and Edge Points.

Synthetic aperture radar (SAR) image registration is an important process in many applications, such as image stitching and remote sensing surveillance. The registration accuracy is commonly affected by the presence of speckle noise in SAR images. When speckle noise is intense, the number of image features acquired by single-feature-based methods is insufficient. An SAR image registration method that combines nonlinear diffusion filtering, Hessian features and edge points is proposed in this paper to reduce speckle noise and obtain more image features. The proposed method uses the infinite symmetric exponential filter (ISEF) for image pre-processing and nonlinear diffusion filtering for scale-space construction. These measures can remove speckle noise from SAR images while preserving image edges. Hessian features and edge points are also employed as image features to optimize the utilization of feature information. Experiments with different noise levels, geometric transformations and image scenes demonstrate that the proposed method effectively improves the accuracy of SAR image registration compared with the SIFT-OCT, SAR-SIFT, Harris-SIFT, NF-Hessian and KAZE-SAR algorithms.

Range-Dependent Channel Calibration for High-Resolution Wide-Swath Synthetic Aperture Radar Imagery.

High-resolution and wide-swath (HRWS) synthetic aperture radar (SAR) imaging with azimuth multi-channel always suffers from channel phase and amplitude errors. Compared with spatial-invariant error, the range-dependent channel phase error is intractable due to its spatial dependency characteristic. This paper proposes a novel parameterized channel equalization approach to reconstruct the unambiguous SAR imagery. First, a linear model is established for the range-dependent channel phase error, and the sharpness of the reconstructed Doppler spectrum is used to measure the unambiguity quality. Furthermore, the intrinsic relationship between the channel phase errors and the sharpness is revealed, which allows us to estimate the optimal parameters by maximizing the sharpness of the reconstructed Doppler spectrum. Finally, the results from real-measured data show that the suggested method performs exceptionally for ambiguity suppression in HRWS SAR imaging.

Full-Scale Aggregated MobileUNet: An Improved U-Net Architecture for SAR Oil Spill Detection.

Oil spills are a major threat to marine and coastal environments. Their unique radar backscatter intensity can be captured by synthetic aperture radar (SAR), resulting in dark regions in the images. However, many marine phenomena can lead to erroneous detections of oil spills. In addition, SAR images of the ocean include multiple targets, such as sea surface, land, ships, and oil spills and their look-alikes. The training of a multi-category classifier will encounter significant challenges due to the inherent class imbalance. Addressing this issue requires extracting target features more effectively. In this study, a lightweight U-Net-based model, Full-Scale Aggregated MobileUNet (FA-MobileUNet), was proposed to improve the detection performance for oil spills using SAR images. First, a lightweight MobileNetv3 model was used as the backbone of the U-Net encoder for feature extraction. Next, atrous spatial pyramid pooling (ASPP) and a convolutional block attention module (CBAM) were used to improve the capacity of the network to extract multi-scale features and to increase the speed of module calculation. Finally, full-scale features from the encoder were aggregated to enhance the network's competence in extracting features. The proposed modified network enhanced the extraction and integration of features at different scales to improve the accuracy of detecting diverse marine targets. The experimental results showed that the mean intersection over union (mIoU) of the proposed model reached more than 80% for the detection of five types of marine targets including sea surface, land, ships, and oil spills and their look-alikes. In addition, the IoU of the proposed model reached 75.85 and 72.67% for oil spill and look-alike detection, which was 18.94% and 25.55% higher than that of the original U-Net model, respectively. Compared with other segmentation models, the proposed network can more accurately classify the black regions in SAR images into oil spills and their look-alikes. Furthermore, the detection performance and computational efficiency of the proposed model were also validated against other semantic segmentation models.

A Sparse Recovery Algorithm for Suppressing Multiple Linear Frequency Modulation Interference in the Synthetic Aperture Radar Image Domain.

In synthetic aperture radar (SAR) signal processing, compared with the raw data of level-0, level-1 SAR images are more readily accessible and available in larger quantities. However, an amount of level-1 images are affected by radio frequency interference (RFI), which typically originates from Linear Frequency Modulation (LFM) signals emitted by ground-based radars. Existing research on interference suppression in level-1 data has primarily focused on two methods: transforming SAR images into simulated echo data for interference suppression, or focusing interference in the frequency domain and applying notching filters to reduce interference energy. However, these methods overlook the effective utilization of the interference parameters or are confined to suppressing only one type of LFM interference at a time. In certain SAR images, multiple types of LFM interference manifest bright radiation artifacts that exhibit varying lengths along the range direction while remaining constant in the azimuth direction. It is necessary to suppress multiple LFM interference on SAR images when original echo data are unavailable. This article proposes a joint sparse recovery algorithm for interference suppression in the SAR image domain. In the SAR image domain, two-dimensional LFM interference typically exhibits differences in parameters such as frequency modulation rate and pulse width in the range direction, while maintaining consistency in the azimuth direction. Based on this observation, this article constructs a series of focusing operators for LFM interference in SAR images. These operators enable the sparse representation of dispersed LFM interference. Subsequently, an optimization model is developed that can effectively suppress multi-LFM interference and reduce image loss with the assistance of a regularization term in the image domain. Simulation experiments conducted in various scenarios validate the superior performance of the proposed method.

Accurate Range Modeling for High-Resolution Spaceborne Synthetic Aperture Radar.

Spaceborne synthetic aperture radar (SAR) is an advanced microwave imaging technology that provides all-weather and all-day target information. However, as spaceborne SAR resolution improves, traditional echo signal models based on airborne SAR design become inadequate due to the curved orbit, Earth rotation, and increased propagation distance. In this study, we propose an accurate range model for high-resolution spaceborne SAR by analyzing motion trajectory and Doppler parameters from the perspective of the space geometry of spaceborne SAR. We evaluate the accuracy of existing range models and propose an advanced equivalent squint range model (AESRM) that accurately fits the actual range history and compensates for high-order term errors by introducing third-order and fourth-order error terms while maintaining the simplicity of the traditional model. The proposed AESRM's concise two-dimensional frequency spectrum form facilitates the design of imaging algorithms. Point target simulations confirm the effectiveness of the proposed AESRM, demonstrating significant improvements in fitting accuracy for range histories characterized by nonlinear trajectories. The developed AESRM provides a robust foundation for designing imaging algorithms and enables higher resolution and more accurate radar imaging.

Identifying influence factors and thresholds of the next day's pollen concentration in different seasons using interpretable machine learning.

The prevalence of pollen allergies is a pressing global issue, with projections suggesting that half of the world's population will be affected by 2050 according to the estimation of the World Health Organization (WHO). Accurately forecasting pollen allergy risks requires identifying key factors and their thresholds for aerosol pollen. To address this, we developed a technical framework combining advanced machine learning and SHapley Additive exPlanations (SHAP) technology, focusing on Beijing. By analyzing meteorological data and vegetation phenology, we identified the factors influencing next-day's pollen concentration (NDP) in Beijing and their thresholds. Our results highlight vegetation phenology data from Synthetic Aperture Radar (SAR), temperature, wind speed, and atmospheric pressure as crucial factors in spring. In contrast, the Normalized Difference Vegetation Index (NDVI), air temperature, and wind speed are significant in autumn. Leveraging SHAP technology, we established season-specific thresholds for these factors. Our study not only confirms previous research but also unveils seasonal variations in the relationship between radar-derived vegetation phenology data and NDP. Additionally, we observe seasonal fluctuations in the influence patterns and threshold values of daily air temperatures on NDP. These insights are pivotal for improving pollen concentration prediction accuracy and managing allergic risks effectively.

A data driven oil spill mapping using GMM clustering and damping ratio on X-Press Pearl ship disaster in the Indian Ocean.

The work presented in this paper is focused on the largest marine disaster to have occurred in the Indian Ocean due to the breakup of the container tanker ship X-Press Pearl. In order to identify the oil spill and its temporal evolution, a recently proposed damping ratio (DR) index is employed. To derive the DR, a data-driven GMM-EM clustering method optimized by stochastic ordering of the resulting classes in Sentinel 1 SAR time series imagery is proposed. A ship-born oil spill site is essentially considered to consist of three subsites: oil, open sea, and ship. The initial site probability densities were determined by using k-means clustering. In addition to the clustering method, two histogram-based approaches, namely contextual peak thresholding (CPT) and contextual peak ordering (CPO), were also formulated and presented. The improved histogram peak detection methods take into account spatial and contextual dependencies. The similarity of the marginal probability densities of the open sea and the oil classes makes it difficult to quantify the DR values to show the level of dampening. In the study, we show that reasonable class separability to correctly determine the σVV0,seaθ is possible by using GMM clustering. Resulting class separability's are also reported using JM and ML distances. The methods tested show the range of derived DR values stays significantly within similar ranges to each other. The outcomes were tested with the ground-based surveys conducted during the disaster for oil spill sites and other chemical compounds. The proposed methods are simple to execute, robust, and fully automated. Further, they do not require masking the oil or the selection of high-confidence water pixels manually.

Sub-Nyquist SAR Imaging and Error Correction Via an Optimization-Based Algorithm.

Sub-Nyquist synthetic aperture radar (SAR) based on pseudo-random time-space modulation has been proposed to increase the swath width while preserving the azimuthal resolution. Due to the sub-Nyquist sampling, the scene can be recovered by an optimization-based algorithm. However, these methods suffer from some issues, e.g., manually tuning difficulty and the pre-definition of optimization parameters, and a low signal-noise ratio (SNR) resistance. To address these issues, a reweighted optimization algorithm, named pseudo-ℒ0-norm optimization algorithm, is proposed for the sub-Nyquist SAR system in this paper. A modified regularization model is first built by applying the scene prior information to nearly acquire the number of nonzero elements based on Bayesian estimation, and then this model is solved by the Cauchy-Newton method. Additionally, an error correction method combined with our proposed pseudo-ℒ0-norm optimization algorithm is also present to eliminate defocusing in the motion-induced model. Finally, experiments with simulated signals and strip-map TerraSAR-X images are carried out to demonstrate the effectiveness and superiority of our proposed algorithm.

Labeled dataset for training despeckling filters for SAR imagery.

When training Artificial Intelligence and Deep Learning models, especially by using Supervised Learning techniques, a labeled dataset is required to have an input with data and its corresponding labeled output data. In the case of images, for classification, segmentation, or other processing tasks, a pair of images is required in the same sense, one image as an input (the noisy image) and the desired (the denoised image) one as an output. For SAR despeckling applications, the common approach is to have a set of optical images that then are corrupted with synthetic noise, since there is no ground truth available. The corrupted image is considered the input and the optical one is the noiseless one (ground truth). In this paper, we provide a dataset based on actual SAR images. The ground truth was obtained from SAR images of Sentinel 1 of the same region in different instants of time and then they were processed and merged into one single image that serves as the output of the dataset. Every SAR image (noisy and ground truth) was split into 1600 images of 512 × 512 pixels, so a total of 3200 images were obtained. The dataset was also split into 3000 for training and 200 for validation, all of them available in four labeled folders.

Coastal Vulnerability Index sensitivity to shoreline position and coastal elevation parameters in the Niger Delta region, Nigeria.

It is imperative to assess coastal vulnerability to safeguard coastal areas against extreme events and sea-level rise. In the Niger Delta region, coastal vulnerability index assessment in the past focused on open-access parameters without comparing the open-access parameters, especially coastal elevation and shoreline change. This sensitivity to the shoreline method and open-access coastal elevation limits the information for the planning of coastal adaptation. The area under investigation is the Niger Delta, which is distinguished by its low-lying coastal plains and substantial ecological and economic significance. In light of the selected parameters, Sentinel-1 GRD images from 2015 to 2022 during high tidal conditions were used to delineate the shoreline position and change rate. Also, different open-access DEMs were used to derive the coastal elevation using the Geographic Information System (GIS) approach. The study employs 5 parameters, such as shorelines obtained from Sentinel-1 SAR images and several Digital Elevation Models (DEMs), geomorphology, mean sea level rise, significant wave height, and mean tide range, in conjunction with the initial Coastal Vulnerability Index (CVI) approach. The study reveals that the type of DEM used significantly influences the coastal elevation ranking and, subsequently, the CVI. Differences in shoreline change rate estimation methods (EPR and LRR) also impact the vulnerability rankings but to a lesser extent. The findings highlight that 40.1% to 58.9% of the Niger Delta coastline is highly or very highly vulnerable to sea-level rise, depending on the shoreline change rate or DEM used. The study underscores the potential of using CVI methods with open-access data in data-poor countries for identifying vulnerable coastal areas that may need protection or adaptation. Lastly, it points out the need for higher resolution DEMs.

Context-aware SAR image ship detection and recognition network.

With the development of deep learning, synthetic aperture radar (SAR) ship detection and recognition based on deep learning have gained widespread application and advancement. However, there are still challenging issues, manifesting in two primary facets: firstly, the imaging mechanism of SAR results in significant noise interference, making it difficult to separate background noise from ship target features in complex backgrounds such as ports and urban areas; secondly, the heterogeneous scales of ship target features result in the susceptibility of smaller targets to information loss, rendering them elusive to detection. In this article, we propose a context-aware one-stage ship detection network that exhibits heightened sensitivity to scale variations and robust resistance to noise interference. Then we introduce a Local feature refinement module (LFRM), which utilizes multiple receptive fields of different sizes to extract local multi-scale information, followed by a two-branch channel-wise attention approach to obtain local cross-channel interactions. To minimize the effect of a complex background on the target, we design the global context aggregation module (GCAM) to enhance the feature representation of the target and suppress the interference of noise by acquiring long-range dependencies. Finally, we validate the effectiveness of our method on three publicly available SAR ship detection datasets, SAR-Ship-Dataset, high-resolution SAR images dataset (HRSID), and SAR ship detection dataset (SSDD). The experimental results show that our method is more competitive, with AP50s of 96.3, 93.3, and 96.2% on the three publicly available datasets, respectively.

Integrating Target and Shadow Features for SAR Target Recognition.

Synthetic aperture radar (SAR) sensor often produces a shadow in pairs with the target due to its slant-viewing imaging. As a result, shadows in SAR images can provide critical discriminative features for classifiers, such as target contours and relative positions. However, shadows possess unique properties that differ from targets, such as low intensity and sensitivity to depression angles, making it challenging to extract depth features from shadows directly using convolutional neural networks (CNN). In this paper, we propose a new SAR image-classification framework to utilize target and shadow information comprehensively. First, we design a SAR image segmentation method to extract target regions and shadow masks. Second, based on SAR projection geometry, we propose a data-augmentation method to compensate for the geometric distortion of shadows due to differences in depression angles. Finally, we introduce a feature-enhancement module (FEM) based on depthwise separable convolution (DSC) and convolutional block attention module (CBAM), enabling deep networks to fuse target and shadow features adaptively. The experimental results on the Moving and Stationary Target Acquisition and Recognition (MSTAR) dataset show that when only using target and shadow information, the published deep-learning models can still achieve state-of-the-art performance after embedding the FEM.

System Design and Echo Preprocessing of Spaceborne Squinted Two-Dimensional Beam Scanning Synthetic Aperture Radar.

Conventional squinted sliding spotlight synthetic aperture radar (SAR) imaging suffers from substantial swath width reduction and complex processing requirements due to the continuous variation in the squint angle and the large range cell migration (RCM) throughout the data acquisition interval. A novel two-dimensional (2D) beam scanning mode for high-resolution wide swath (HRWS) imaging is proposed. The key to the novel imaging mode lies in the synchronous scanning of azimuth and range beams, allowing for a broader and more flexible imaging swath with a high geometric resolution. Azimuth beam scanning from fore to aft was used to improve the azimuth resolution, while range beam scanning was adopted to illuminate the oblique wide swath to avoid the large RCM and the serious swath width reduction. Compared with the conventional sliding spotlight mode, both the swath width and swath length could be extended. According to the echo model of this imaging mode, an echo signal preprocessing approach is proposed. The key points of this approach are range data extension and azimuth data upsampling. A designed system example with a resolution of 0.5 m, swath width of 60 km, and azimuth coverage length of 134 km is presented. Furthermore, a simulation experiment on point targets was carried out. Both the presented system example and imaging results of point targets validated the proposed imaging mode.

Comparison of Imaging Radar Configurations for Roadway Inspection and Characterization.

This paper investigates the performance of a wide variety of radar imaging modes, such as nadir-looking B-scan, or side-looking synthetic aperture radar tomographic acquisitions, performed in both back- and forward-scattering geometries, for the inspection and characterization of roadways. Nadir-looking B-scan corresponds to a low-complexity mode exploiting the direct return from the response, whereas side-looking configurations allow the utilization of angular and polarimetric diversity in order to analyze advanced features. The main objective of this paper is to evaluate the ability of each configuration, independently of aspects related to operational implementation, to discriminate and localize shallow underground defects in the wearing course of roadways, and to estimate key geophysical parameters, such as roughness and dielectric permittivity. Campaign measurements are conducted using short-range radar stepped-frequency continuous-waveform (SFCW) devices operated in the C and X bands, at the pavement fatigue carousel of Université Gustave Eiffel, over debonded areas with artificial defects. The results indicate the great potential of the newly proposed forward-scattering tomographic configuration for detecting slight defects and characterizing roadways. Case studies, performed in the presence of narrow horizontal heterogeneities which cannot be detected using classical B-scan, show that both the coherent integration along an aperture using the back-projection algorithm, and the exploitation of scattering mechanisms specific to the forward-looking bistatic geometry, allows anomalous echoes to be detected and further characterized, confirming the efficacy of radar imaging techniques in such applications.

iVision MRSSD: A comprehensive multi-resolution SAR ship detection dataset for state of the art satellite based maritime surveillance applications.

This article describes a comprehensive Synthetic Aperture Radar (SAR) satellite based ships dataset for use in state of the art object detection algorithms. The dataset comprises 11,590 image tiles containing 27,885 ships examples. Each image tile has spatial dimensions of 512 × 512 pixels and is exported in JPEG format. The dataset contains a wide variety of inshore and offshore scenes under varying background settings and sea conditions to generate an all-inclusive understanding of the ship detection task in SAR satellite images. The dataset is generated using images from six different satellite sensors covering a wide range of electromagnetic spectrum including C, L and X band radar imaging frequencies. All the sensors have different resolutions and imaging modes. The dataset is randomly distributed into training, validation and test sets in the ratio of 70:20:10, respectively, for ease of comparison and bench-marking. The dataset was conceptualized, processed, labeled and verified at the Artificial Intelligence and Computer Vision (iVision) Lab at the Institute of Space Technology, Pakistan. To the best of our knowledge, this is the most diverse satellite based SAR ships dataset available in the public domain in terms of satellite sensors, radar imaging frequencies and background settings. The dataset can be used to train and optimize deep learning based object detection algorithms to develop generic models with high detection performance for any SAR sensor and background condition.

FCCD-SAR: A Lightweight SAR ATR Algorithm Based on FasterNet.

In recent times, the realm of remote sensing has witnessed a remarkable surge in the area of deep learning, specifically in the domain of target recognition within synthetic aperture radar (SAR) images. However, prevailing deep learning models have often placed undue emphasis on network depth and width while disregarding the imperative requirement for a harmonious equilibrium between accuracy and speed. To address this concern, this paper presents FCCD-SAR, a SAR target recognition algorithm based on the lightweight FasterNet network. Initially, a lightweight and SAR-specific feature extraction backbone is meticulously crafted to better align with SAR image data. Subsequently, an agile upsampling operator named CARAFE is introduced, augmenting the extraction of scattering information and fortifying target recognition precision. Moreover, the inclusion of a rapid, lightweight module, denoted as C3-Faster, serves to heighten both recognition accuracy and computational efficiency. Finally, in cognizance of the diverse scales and vast variations exhibited by SAR targets, a detection head employing DyHead's attention mechanism is implemented to adeptly capture feature information across multiple scales, elevating recognition performance on SAR targets. Exhaustive experimentation on the MSTAR dataset unequivocally demonstrates the exceptional prowess of our FCCD-SAR algorithm, boasting a mere 2.72 M parameters and 6.11 G FLOPs, culminating in an awe-inspiring 99.5% mean Average Precision (mAP) and epitomizing its unparalleled proficiency.