Traditional Detection Research Articles

An Intelligent Kick Detection Model for Large-Hole Ultra-Deep Wells in the Sichuan Basin

The Sichuan Basin has abundant deep and ultra-deep natural gas resources, making it a primary target for exploration and the development of China’s oil and gas industry. However, during the drilling of ultra-deep wells in the Sichuan Basin, complex geological conditions frequently lead to gas kicks, posing significant challenges to well control and safety. Compared to traditional kick detection methods, artificial intelligence technology can improve the accuracy and timeliness of kick detection. However, there are limited real-world kick data available from drilling operations, and the datasets are extremely imbalanced, making it difficult to train intelligent models with sufficient accuracy and generalization capabilities. To address this issue, this paper proposes a kick data augmentation method based on a time-series generative adversarial network (TimeGAN). This method generates synthetic kick samples from real datasets and then employs a long short-term memory (LSTM) neural network to extract multivariate time-series features of surface drilling parameters. A multilayer perceptron (MLP) network is used for data classification tasks, constructing an intelligent kick detection model. Using real drilling data from ultra-deep wells in the SY block of the Sichuan Basin, the effects of k-fold cross-validation, data dimensionality, various imbalanced data handling techniques, and the sample imbalance ratio on the model’s kick detection performance are analyzed. Ablation experiments are also conducted to assess the contribution of each module in identifying kick. The results show that TimeGAN outperforms other imbalanced data handling techniques. The accuracy, recall, precision, and F1-score of the kick identification model are highest when the sample imbalance ratio is at 1 but decrease as the imbalance ratio increases. This indicates that maintaining a balance between positive and negative samples is essential for training a reliable intelligent kick detection model. The trained model is applied during the drilling of seven ultra-deep wells in Sichuan, demonstrating its effectiveness and accuracy in real-world kick detection.

Rapid detection of enterobacteria in wastewater treated by microalgal consortia using loop-mediated isothermal amplification (LAMP)

In the present study, nine Enterobacteriaceae species present in wastewater were isolated and identified, and loop-mediated isothermal amplification (LAMP) was developed for the detection of Enterobacteriaceae by designing primers based on the mcr-1, KPC, OXA-23, and VIM genes, which are recognized markers of antimicrobial resistance (AMR) transmission during microalgal bioremediation treatment. The developed assays successfully detected four strains positive for mcr-1 gene-asociated resistance (Acinetobacter baylyi, Klebsiella pneumoniae, Morganella morganii, and Serratia liquefaciens), three strains for KPC gene-associated resistance (Acinetobacter sp., Escherichia coli 15499, and Morganella morganii), seven strains for OXA-23 gene-associated resistance (Acinetobacter baylyi, Enterobacter hormaechi, Enterobacter cloacae, Escherichia coli 15922, Escherichia coli 51446, Morganella morganii, and Serratia liquefaciens), and three strains for resistance to the VIM gene-associated resistance (Acinetobacter baylyi, Acinetobacter sp., and Enterobacter hormaechi) from a single colony. A reduction in microbiological load of 93.6% was achieved at 15 colony-forming units (CFU) mL−1, utilizing EMB agar and LAMP values of 0.142 ± 0.011 for the mcr-1 gene, 0.212 ± 0.02 for the KPC gene, 0.233 ± 0.006 for the OXA-23 gene, and 0.219 ± 0.035 for the VIM gene. Furthermore, bioremediation efficiency values of 71.6% and 75% for total nitrogen and phosphorus, respectively, were observed at 72 h of treatment in open pond microalgal remediation systems (MRS). This study demonstrated that the LAMP technique is faster and more sensitive than traditional detection methods, such as CFU, for Enterobacteriaceae. Consequently, this method may be considered for the detection of microbiological quality indicators within the water treatment industry.

Establishment and Application of a New Radiation Biodosimetric Method Based on the Quantitative RPA-SHERLOCK Amplification Technology.

Biodosimetry is a key diagnostic tool for radiation exposure, risk assessment and treatment planning of acute radiation sickness. To effectively respond to a large-scale radiological incident, there is a need for the development of biodosimetric methods with fast, portable, and convenient operating advantages. We employed the recombinase polymerase amplification specific high-sensitivity enzymatic reporter unlocking (RPA-SHERLOCK) technology to establish a method for fast radiation dose assessment by measuring the expression level of radiation-inducible genes. Moreover, we proposed for the first time the principle of quantitative detection of curve slopes based on this method. Using this new method, changes in mRNA expression were confirmed in a number of radiation-sensitive genes (XPC, CDKN1A, and ATM) in human lymphocytes after irradiation. The standard curve of the dose-effect relationship was established, which can be used to quickly determine the exposed dose of the irradiated samples. Compared with traditional detection methods such as RT-qPCR, this method was found to be more convenient, fast and easy to operate. With the same amount of template input as RT-qPCR, the detection time of this method can be shortened to less than 20 min. The detection instrument required by this method is also more portable than a qPCR system.

A dynamic neural network model for the identification of asbestos roofings in hyperspectral images covering a large regional area

AbstractAsbestos has been used extensively in several applications. Once it is known as a dangerous mineral, its usage has been prohibited and its identification and remediation play a very important role from the health safety point of view. Nowadays, deep learning techniques are used in many applications, especially for image analysis. They can be used to significantly reduce the time and cost of traditional detection methods. In this paper, taking advantage of asbestos spectral signature, a deep neural network is introduced in order to implement a complete methodology to identify asbestos roofings starting from hyperspectral images in a regional context. The novelty of the proposed approach is a dynamic mixing of models with different features, in order to accommodate classifications on widespread areas of both urban and rural territories. Indeed, the dataset used during the experiments described in this paper is a large one, consisting of many wide hyperspectral images with a geometric resolution of 1 m and with 186 bands, covering an entire region of approximately 8,000 . This is in contrast to other works in the literature where the analyzed areas are limited in size and uniform for physical features.

Network-Based Intrusion Detection for Industrial and Robotics Systems: A Comprehensive Survey

In the face of rapidly evolving cyber threats, network-based intrusion detection systems (NIDS) have become critical to the security of industrial and robotic systems. This survey explores the specialized requirements, advancements, and challenges unique to deploying NIDS within these environments, where traditional intrusion detection systems (IDS) often fall short. This paper discusses NIDS methodologies, including machine learning, deep learning, and hybrid systems, which aim to improve detection accuracy, adaptability, and real-time response. Additionally, this paper addresses the complexity of industrial settings, limitations in current datasets, and the cybersecurity needs of cyber–physical Systems (CPS) and Industrial Control Systems (ICS). The survey provides a comprehensive overview of modern approaches and their suitability for industrial applications by reviewing relevant datasets, emerging technologies, and sector-specific challenges. This underscores the importance of innovative solutions, such as federated learning, blockchain, and digital twins, to enhance the security and resilience of NIDS in safeguarding industrial and robotic systems.

Multi-Agent Locally Trained Progressive Instance Selected Assisted Federated Learning Architecture for Intrusion Detection in Industrial-IoT

In this work the focus is made on designing and developing a robust federated learning model (FLM) and architecture for multi-type network intrusion detection system (MT-NIDS) for IIoT applications. Unlike traditional intrusion detection systems, where the key focus is made on detecting and classifying single type of intrusion or attack condition, this research targets to perform multi-type network intrusion detection. This as a result can contribute a fit-to-all NIDS solution for IIoT environment.

A semi-automated method using object-based image analysis (OBIA) to detect and enumerate beluga whales in summer from very high-resolution (VHR) satellite imagery.

Very high-resolution (VHR) satellite imagery has proven to be useful for detection of large to medium cetaceans, such as odontocetes and offers some significant advantages over traditional detection methods. However, the significant time investment needed to manually read satellite imagery is currently a limiting factor to use this method across large open ocean regions. The objective of this study is to develop a semi-automated detection method using object-based image analysis to identify beluga whales (Delphinapterus leucas) in open water (summer) ocean conditions in the Arctic using panchromatic WorldView-3 satellite imagery and compare the detection time between human read and algorithm detected imagery. The false negative rate, false positive rate, and automated count deviation were used to assess the accuracy and reliability of various algorithms for reading training and test imagery. The best algorithm, which used spectral mean and texture variance attributes, detected no false positives and the false negative rate was low (<4%). This algorithm was able to accurately and reliably identify all the whales detected by experienced readers in the ice-free panchromatic image. The autodetection algorithm does have difficulty separately identifying whales that are perpendicular to one another, whales below the surface, and may use multiple segments to define a whale. As a result, for determining counts of whales, a reader should manually review the automated results. However, object-based image analysis offers a viable solution for processing large amounts of satellite imagery for detecting medium-sized beluga whales while eliminating all areas of the imagery which are whale-free. This algorithm could be adapted for detecting other cetaceans in ice-free water.

An innovative traffic flow detection model based on temporal video frame analysis and grayscale aggregation quantification

AbstractCurrent traffic status detection methods heavily rely on historical traffic flow data and vehicle counts. However, these methods often fail to meet the stringent real‐time requirements of state detection, especially on edge devices with limited computing resources.To address these challenges, this study develops a traffic alert model using temporal video frame analysis and grayscale aggregation quantization techniques. Initially, the model uses distance mapping between pixel features and frames of road traffic videos to construct a comprehensive road environment and vehicle segmentation model. The model also establishes a mapping between pixel equidistant lines and actual distances, enabling precise congestion detection. This approach significantly reduces costs associated with traditional traffic detection methods as it does not rely on historical data. Performance evaluation using fixed‐point road monitoring data indicates that the proposed model outperforms traditional traffic state detection models, with a performance improvement of approximately 4.7% to 9.5%. Additionally, the model improves computing resource efficiency by approximately 72.5% and demonstrates substantial real‐time detection capabilities.

Development of an internet-of-things-based controlled-source ultrasonic audio frequency electromagnetic receiver

Abstract. Electromagnetic exploration, characterized by its low cost, wide applicability, and high operational efficiency, finds extensive applications in fields such as oil and gas exploration, mineral prospecting, and engineering geology. Traditional controlled-source electromagnetic detection methods are typically confined to operating frequencies below 250 kHz, resulting in insufficient detection accuracy for applications such as shallow- and intermediate-depth exploration, thereby constraining their performance in high-resolution imaging. To address these challenges, we propose a controlled-source ultrasonic audio frequency electromagnetic receive system based on the internet of things (IoT). We investigate cascaded digital filtering and sampling techniques to extend the receiver's sampling rate range, thereby elevating the operating frequency of controlled-source electromagnetic acquisition from the conventional maximum of 250 kHz to 1 MHz. The receiver achieves a sampling rate of up to 2.5 MHz, comprising three magnetic field measurement channels and two electric field measurement channels. The instrument is compact, lightweight, and capable of real-time data storage locally and real-time data transmission to an upper computer. Additionally, IoT technology is introduced, leading to the design of a cloud-based real-time remote control and data acquisition scheme. Experimental results demonstrate the stability of the instrument, meeting the requirements of field exploration.

Exploring the Application of Large Language Models Based AI Agents in Leakage Detection of Natural Gas Valve Chambers

Leakage problems occur from time to time due to the large number of equipment and complex processes during oil and gas production and transportation. The traditional detection methods highly depend on manpower with large workload and are prone to missed and false alarms, which seriously affects the efficiency and safety of oil and gas production and transportation. With the continuous improvement of information technology and the rapid advancement of artificial intelligence (AI), the research on leakage detection technology based on AI methods has attracted more and more attention. This paper discusses the application scenarios of an AI agent based on the recently emerged large language model (LLM) technology in oil and gas production leakage detection: (1) Compared with the traditional leakage detection methods, this paper innovatively employs a combination of AI-based diagnostics and infrared temperature measurement technologies to develop a specialized small model for oil and gas leakage detection, which has been proven to significantly improve the accuracy of detecting industrial venting events in natural gas valve chambers; (2) By employing retrieval-augmented generation (RAG) technology, a knowledge vector library is constructed, utilizing a series of leakage-related documents, assisting the LLM to carry out knowledge questioning and inference. Compared with the traditional SimBERT, the accuracy can be improved by about 15% in the Q&amp;A search ability test. The correct rate is about 70% higher than the SimBERT in the Chinese complex reasoning quiz. Also, it can still remain stable under high load conditions, with the interruption rate of retrieval closing to zero. (3) By combining the specialized small model and the knowledge Q&amp;A tool, the natural gas valve chambers’ leakage detection AI agent based on the open-source LLM model was designed and developed, which preliminarily achieved the leakage detection based on the specialized small model, and the automatic processing of the retrieval reasoning process based on the knowledge Q&amp;A tool and the intelligent generation of corresponding leakage disposal scheme. The effectiveness of the method has been verified by actual project data. This article conducts preliminary explorations into the in-depth applications of AI agents based on LLMs in the oil and gas energy industry, demonstrating certain positive outcomes.

Recent Advances in Mycotoxin Detection: A Review

Mycotoxins, toxic compounds produced by fungi like Aspergillus and Penicillium, pose significant health risks even at low concentrations. Detecting these contaminants in food requires intricate methods due to their low levels and complex sample matrices. Historically, toxic fungi research began with mushrooms but expanded in the mid-1800s to include other fungi, such as Claviceps purpurea, which caused ergotism through contaminated rye. Mycotoxins severely impact both human and animal health, causing issues like cancer, immune suppression, and nervous system damage, while also disrupting global food trade, affecting around 25% of crops worldwide. Traditional detection methods include chromatography (TLC, LC, GC, HPLC) and immunological assays like ELISA and LFI, though these methods have limitations. Recent advances in mycotoxin detection feature innovations like biosensors, fluorescence-based techniques, phage display technology, and smartphone-enabled systems, which offer enhanced sensitivity, specificity, and rapid detection capabilities. These methods represent a promising shift towards more efficient and precise mycotoxin analysis in food safety.

DeepFake Image Detection: Fake Image Detection using CNNs and GANs Algorithm

Deep learning is a powerful and versatile technique that has seen extensive applications in areas such as natural language processing, machine learning, and computer vision. Among its most recent applications is the generation of deepfakes, which are high-quality, realistic altered videos or images that have garnered significant attention. While innovative uses of deepfake technology are being explored, its potential for misuse has raised serious concerns. Harmful applications, such as spreading fake news, creating celebrity pornography, financial fraud, and revenge pornography, have become increasingly prevalent in the digital age. As a result, public figures, including celebrities and politicians, face heightened risks from deepfake content. In response, substantial research has been conducted to explore the mechanics behind deepfakes, leading to the development of various deep learning-based algorithms for their detection. This study provides a comprehensive review of deepfake creation and detection techniques, focusing on different deep learning approaches. Additionally, it discusses the limitations of existing methods and the availability of datasets for research. The lack of a highly accurate and fully automated deepfake detection system presents a significant challenge as the ease of generating and distributing such content continues to grow. Nonetheless, recent efforts in deep learning have shown promising results, surpassing traditional detection methods.

Fire Fighter Robot Using IOT and Mobile Application

In today's fast-paced world, fire hazards pose significant risks to life, property, and the environment. Traditional fire detection systems often rely on human intervention, leading to delays in response time and exacerbating the damage caused by fire incidents. Our project, the IoT-Based Automatic Fire Detection and Extinguisher Robot, addresses this challenge by utilizing a combination of modern sensor technology, robotics, and IoT to provide an autonomous and real-time solution. The robot is equipped with flame and temperature sensors that allow it to detect fires at an early stage. Once a fire is detected, the robot activates its movement mechanism using DC motors to navigate toward the fire while the integrated servo-controlled water pump precisely sprays water to extinguish the fire. In addition to automatic firefighting, the robot features obstacle detection using ultrasonic sensors, ensuring safe navigation in complex environments. The system includes Bluetooth and Wi-Fi communication, allowing for remote control via an Android mobile app. This app provides both manual and automatic control options and sends real-time fire alerts when the robot detects a fire. This autonomous system minimizes human intervention, speeds up response times, and reduces fire damage effectively. The robot is powered by an ESP32 microcontroller, which processes data from the sensors and controls the motors and water pump. The rescue pod feature allows the robot to perform additional operations like transporting sensitive materials during emergencies. The system's IoT functionality enables real-time alerts and remote monitoring, enhancing its capability as a scalable and cost-effective solution for residential, commercial, and industrial fire safety.

A Deep Learning Model for Accurate Maize Disease Detection Based on State-Space Attention and Feature Fusion

In improving agricultural yields and ensuring food security, precise detection of maize leaf diseases is of great importance. Traditional disease detection methods show limited performance in complex environments, making it challenging to meet the demands for precise detection in modern agriculture. This paper proposes a maize leaf disease detection model based on a state-space attention mechanism, aiming to effectively utilize the spatiotemporal characteristics of maize leaf diseases to achieve efficient and accurate detection. The model introduces a state-space attention mechanism combined with a multi-scale feature fusion module to capture the spatial distribution and dynamic development of maize diseases. In experimental comparisons, the proposed model demonstrates superior performance in the task of maize disease detection, achieving a precision, recall, accuracy, and F1 score of 0.94. Compared with baseline models such as AlexNet, GoogLeNet, ResNet, EfficientNet, and ViT, the proposed method achieves a precision of 0.95, with the other metrics also reaching 0.94, showing significant improvement. Additionally, ablation experiments verify the impact of different attention mechanisms and loss functions on model performance. The standard self-attention model achieved a precision, recall, accuracy, and F1 score of 0.74, 0.70, 0.72, and 0.72, respectively. The Convolutional Block Attention Module (CBAM) showed a precision of 0.87, recall of 0.83, accuracy of 0.85, and F1 score of 0.85, while the state-space attention module achieved a precision of 0.95, with the other metrics also at 0.94. In terms of loss functions, cross-entropy loss showed a precision, recall, accuracy, and F1 score of 0.69, 0.65, 0.67, and 0.67, respectively. Focal loss showed a precision of 0.83, recall of 0.80, accuracy of 0.81, and F1 score of 0.81. State-space loss demonstrated the best performance in these experiments, achieving a precision of 0.95, with recall, accuracy, and F1 score all at 0.94. These results indicate that the model based on the state-space attention mechanism achieves higher detection accuracy and better generalization ability in the task of maize leaf disease detection, effectively improving the accuracy and efficiency of disease recognition and providing strong technical support for the early diagnosis and management of maize diseases. Future work will focus on further optimizing the model’s spatiotemporal feature modeling capabilities and exploring multi-modal data fusion to enhance the model’s application in real agricultural scenarios.

Image splicing detection using integrated LBP and DCT features

Abstract. Image splicing is one of the most common techniques used for picture manipulation and forgery. With the advent of user-friendly photo editing software, image splicing has become more prevalent and increasingly difficult to detect. This paper proposes a passive photo splicing detection approach based on Local Binary Patterns (LBP) and Discrete Cosine Transform (DCT) to identify splicing forgeries. The input RGB images are first converted to the YCbCr color space. Subsequently, the chrominance channels, Cb and Cr, are divided into overlapping blocks. Each block's LBP code is then transformed into the DCT domain. For each block, the standard deviation of each DCT coefficient is computed and used as a feature. Support Vector Machine (SVM) is employed as the classifier in a predictive model to determine whether the images have been spliced. To evaluate the proposed approach, two benchmark datasets for photo tampering were utilized. Experimental results indicate that the proposed method outperforms traditional splicing detection techniques in terms of detection accuracy and performance. This enhanced detection capability underscores the potential of combining LBP and DCT features with SVM classification for robust image splicing detection, paving the way for improved digital forensics tools in combating image manipulation.

Overview of object detection based on deep learning

Abstract. In recent years, computer vision technology has developed rapidly, as one of its important research directions, object detection has received widespread attention due to its high accuracy. Meanwhile, object detection has many application fields, such as intelligent transportation, medical and health, security systems, etc. Traditional object detection methods have limitations when applied to complex real-world scenarios. To improve the shortcomings of conventional methods, deep learning based object detection algorithms have significantly improved the efficiency of object detection and become a research hotspot in object detection. This article summarizes the algorithms into two-stage and one-stage object detection algorithms based on the technical processes and structural differences in handling object detection tasks. Firstly, several common two-stage and one-stage object detection algorithms and their applications in real-world scenarios are introduced. Then their data sets and algorithm performance are analyzed and compared. Finally, according to the results of the comparison, the existing problems of the two-stage object detection algorithm and the one-stage object detection method are discussed, and their future development directions are pointed out.

Hybrid Learning Model for intrusion detection system: A combination of parametric and non-parametric classifiers

The growing digital transformation has increased the need for effective intrusion detection systems. Traditional intrusion detection systems face challenges in accurately classifying complex patterns. To address this issue, this study proposed a Hybrid Learning Model (HLM) that combines both parametric and non-parametric classifiers. The proposed HLM consist of two stages: the first stage employs a non-parametric Base Learner (np-BL) to analyze the data patterns and the second stage involves meta-modelling to generalize the overall performance of the model, named the Parametric Meta-Learning (PML) model. The proposed HLM blends the outcomes of np-BL and PML models using a stacking ensemble. As a base learning model K-Nearest Neighbors (KNN), Decision Tree (DT), Random Forest (RF), Gradient Boosting Machine (GBM), and Support Vector Classification with Radial Basis Function (SVC-RBF), are adopted from a non-parametric classifier group. The parametric classifiers Logistic Regression (LR), Naïve Bayes Classifier (NBC), Linear Discriminant Analysis (LDA), Quadratic Discriminant Analysis (QDA) and Support Vector Machine with linear kernel (Linear SVM) were used as meta-models. The HLM, as proposed, enhances the adaptability and robustness of the model by combining non-parametric and parametric models. To evaluate the competence of the proposed HLM, a performance analysis was conducted using the NSL-KDD, UNSW-NB15, and CICIDS2017 datasets. The effectiveness was assessed using various metrics, including classification accuracy, precision, recall, F1-Score (F1), Receiver Operating Characteristic (ROC) curve, Detection Rate (DR), and False Alarm Rate (FAR). The proposed HLM achieves a better accuracy rate across different datasets when compared with the existing models. The achieved accuracies are 99.02 %, 99.98 % and 99.63 % for the NSL-KDD, UNSW-NB15, and CICIDS2017 datasets respectively. Furthermore, the HLM gave a significant reduction in FAR, with values of 0.0126, 0.0001, and 0.0016 for the above-mentioned datasets.

Research on lane detection algorithms based on GTNs

Abstract. Lane detection technology plays an important role in the lane departure warning and adaptive cruise control functions of autonomous vehicle systems. Traditional lane line detection includes experimental steps such as preyreatment, color space conversion, feature extraction, and lane line tracking, but there are still some problems such as recognition accuracy in complex environments and parameter adjustment dependency. To overcome these limitations, this study uses a novel method that can directly predict the parameters of the lane shape model, thus avoiding complex post-processing steps. This research method uses the network structure based on Graph Transformer Networks (GTNS) to capture richer structural information and contextual relationships, thereby improving the accuracy of detection. In terms of feature extraction, Graph Transformer Networks is used to accurately capture the structural information of the lane through the attention mechanism. At the same time, the results in the later stage show that our method has better advantages in accuracy and speed. In short, this optimization scheme not only improves the detection speed but also ensures a certain degree of accuracy. The method will perform better in the future after further optimization such as multi-sensor fusion and real-time optimization.

Metagenomic next-generation sequencing of osteoarticular tissue for the diagnosis of suspected osteoarticular tuberculosis.

In the detection of unknown infectious disease pathogens, the overall efficacy of traditional detection methods, such as culture, is low, and traditional PCR testing is also limited to the gene sequences of known pathogenic microorganisms. Metagenomic next-generation sequencing (mNGS) performs DNA sequencing by studying the entire microbial community genome in a given sample, without the need for isolation and culture. Previous studies have shown that mNGS performs better on pulmonary and extrapulmonary samples when compared with Xpert, traditional pathogenetic tests, and even parallel diagnostics. However, it should be emphasized that only a few studies have explored the performance of mNGS in detecting Mycobacterium tuberculosis in clinical samples associated with bone and joint infections. We conducted this retrospective study to provide additional data to support the use of mNGS in the clinical setting to identify pathogens within abscesses or tissue samples associated with bone and joint infections.

Impact of RAW vs. RGB images on low-light object detection in autonomous driving

Abstract. In the field of autonomous driving, object detection in low-light conditions presents a critical challenge. Traditional detection algorithms, reliant on RGB imagery, often suffer from diminished performance under inadequate illumination. In contrast, RAW images, which retain a higher level of intrinsic image information, have the potential to enhance detection accuracy. Therefore, the paper aims to assess whether models trained on RAW images exhibit enhanced object detection performance in low-light scenarios. To this end, experiments are conducted utilizing the Low-light Object Detection (LOD) dataset, which includes paired RAW and RGB images, with variations in lighting simulated through different exposure times. Two distinct datasets are constructed: one consisting of RAW-normal and RAW-dark images, and another comprising RGB-normal and RGB-dark images. The models evaluated in this research include YOLOv8, Faster R-CNN (Region-based Convolutional Neural Network), and EfficientDet, selected to ensure robustness and generalizability of the findings. The results demonstrate that models trained on RAW images significantly outperform those trained on RGB images, thus exhibiting higher accuracy both in general and under low-light conditions. The preservation of detailed image information in RAW format facilitates enhanced feature extraction, thereby improving detection accuracy and resilience under low-light conditions. These findings provide novel insights into advancing object detection methodologies for autonomous driving systems operating in challenging lighting environments.