Objects Of Different Sizes Research Articles

CoFiNet: Unveiling camouflaged objects with multi-scale finesse

Camouflaged Object Detection (COD) is a critical aspect of computer vision aimed at identifying concealed objects, with applications spanning military, industrial, medical and monitoring domains. To address the problem of poor detail segmentation effect, we introduce a novel method for camouflaged object detection, named CoFiNet. Our approach primarily focuses on multi-scale feature fusion and extraction, with special attention to the model’s segmentation effectiveness for detailed features, enhancing its ability to effectively detect camouflaged objects. CoFiNet adopts a coarse-to-fine strategy. A multi-scale feature integration module is laveraged to enhance the model’s capability of fusing context feature. A multi-activation selective kernel module is leveraged to grant the model the ability to autonomously alter its receptive field, enabling it to selectively choose an appropriate receptive field for camouflaged objects of different sizes. During mask generation, we employ the dual-mask strategy for image segmentation, separating the reconstruction of coarse and fine masks, which significantly enhances the model’s learning capacity for details. Comprehensive experiments were conducted on four different datasets, demonstrating that CoFiNet achieves state-of-the-art performance across all datasets. The experiment results of CoFiNet underscore its effectiveness in camouflaged object detection and highlight its potential in various practical application scenarios.

Nearshore optical video object detector based on temporal branch and spatial feature enhancement

The computing power of nearshore and ship-borne devices is limited, posing significant challenges for accurately detecting objects in real-time on such devices. We propose a nearshore video object detector (NVID) to tackle these challenges. Considering the abundance of dynamic entities in the nearshore environment, we have developed you can look more (YCLM) to perceive the temporal characteristics of these objects. Furthermore, to improve the ability to detect objects of different sizes of networks, we designed parallel deformable attention (PDA) based on the spatial features of objects. More importantly, we developed fast re-parameterization convolution (FREConv) and faster conv (FConv). Building on these innovations, we proposed a fast re-parameterization network (FRENet) specifically tailored to produce low-parameter, multi-scale feature outputs. With end-to-end training, our pipeline outperforms other state-of-the-art (SOTA) methods on the nearshore objects (NearshoreObjects) dataset (90.4 average precision (AP) 50 (＋4.7), 9.3 parameters (Params) (−1.0M), 24.8 frames per second (FPS) (Jetson Nano) (＋0.6)). In addition, NVID also achieved excellent results in the on board (OnBoard) dataset (90.3 AP50 (＋2.8), 9.3 params (−1.0M), 26.5 FPS (Jetson Nano) (＋0.8)). The source code can be accessed at https://github.com/Yuanlin-Zhao/NVID.

Monocular visual obstacle avoidance method for autonomous vehicles based on YOLOv5 in multi lane scenes

This study explores a more effective obstacle avoidance method for autonomous driving based on the monocular vision system of YOLOv5. The study utilizes the YOLOv5 model to detect obstacles and road signs in the environment in real-time, including vehicles, pedestrians, traffic signals, etc., identifying objects of different sizes and angles, providing accurate obstacle avoidance decision inputs. Then, we use a path planning algorithm based on deep reinforcement learning to combine the detected obstacle information with the current state of the vehicle, dynamically generating safe and efficient driving paths. In order to further improve the obstacle avoidance effect, a monocular visual autonomous driving obstacle avoidance aggregation network was introduced in the study, and the MMA (Multi lane monocular visual autonomous driving) obstacle avoidance method was established. The future movement trend of obstacles was predicted by setting an improved monocular obstacle avoidance loss function to sense historical data and the environment. The experimental results show that MMA has significantly enhanced obstacle avoidance and driving efficiency. The accuracy of the MMA obstacle avoidance method fluctuates between 78.76 % and 88.26 %, showing the best overall performance. The accuracy also shows an upward trend with the increase of the data sample size.

YOLO-SGF: Lightweight network for object detection in complex infrared images based on improved YOLOv8

The current mainstream object detection networks perform well in RGB visible images, but they require high computational resource and degrade in performance when applied to low-resolution infrared images. To address above issues, we propose a lightweight algorithm YOLO-SGF based on you-only-look-once version8 (YOLOv8). Firstly, the lightweight cross-scale feature map fusion network GCFVoV designed as neck to solve poor detection accuracy and maintain low complexity in lightweight networks. And a lightweight GCVF module in GCFVoV neck uses GSConv and Conv to process deep and shallow features respectively, which maximally preserves implicit connections between each channel and integrates multi-scale features. Secondly, we utilize ShuffleNetV2-block1 in combination with C2f for feature extraction, making the algorithm more lightweight and effectively. Finally, we propose the FIMPDIoU loss function, which focuses on overlooked objects in complex backgrounds and adjusts the prediction boxes using ratios specific to different sizes of objects. Compared with YOLOv8 in our infrared dataset, YOLO-SGF reduces the computational space complexity by 50 % and time complexity by 42 %, increases FPS32 by 36.3 % and improves mAP@0.5 ∼ 0.95 by 1.1 % in object detection. Our algorithm enhances the capability of object detection in infrared images especially in nighttime, low light, and occluded conditions. YOLO-SGF enables deployment on embedded edge devices with limited computing power, and provides a new idea for lightweight networks.

Towards higher load capacity: innovative design of a robotic hand with soft jointed structure

In this paper, the innovative design of a robotic hand with soft jointed structure is carried out and a tendon-driven mechanism, a master-slave motor coordinated drive mechanism, a thumb coupling transmission mechanism and a thumb steering mechanism are proposed. These innovative designs allow for more effective actuation in each finger, enhancing the load capacity of the robotic hand while maintaining key performance indicators such as dexterity and adaptability. A mechanical model of the robotic finger was made to determine the application limitations and load capacity. The robotic hand was then prototyped for a set of experiments. The experimental results showed that the proposed theoretical model were reliable. Also, the fingertip force of the robotic finger could reach up to 10.3 N, and the load force could reach up to 72.8 N. When grasping target objects of different sizes and shapes, the robotic hand was able to perform the various power grasping and precision grasping in the Cutkosky taxonomy. Moreover, the robotic hand had good flexibility and adaptability by means of adjusting the envelope state autonomously.

Dynamics of landslides on ice-rich space objects

This work is aimed at investigating the velocity of landslides on ice-containing cosmic bodies of low gravity. We performed a series of experiments dealing with the sliding of desiccated sand on ice and ice-containing mixtures. Measurements were performed in vacuum and at normal pressure in different spatial scales. The values of the velocity derived from the results of experiments were scaled using the gravitational acceleration relevant for the space objects of different sizes: the nuclei of comets and the dwarf planet Ceres. We have found, that the average velocity of material sliding down a hundred meters long slope on the nucleus of a comet should be of the order 0.01 m s−1, while the velocity of dry landslides on Ceres should be two orders of magnitude higher.

Extreme small-scale prediction head-based efficient YOLOV5 for small-scale object detection

Recognition models achieved exceptional performance in object detection during the computer vision era, but they still rely on Small-Scale Object Detection (SSOD). SSOD remains difficult due to the variety of shapes and orientations of the object, as well as fixed prediction heads at the detection stage. To overcome these challenges, our paper proposed an auto anchor module, a Spatial Pyramid Pooling Faster layer (SPPF) in the feature refinement network, and an extremely small-scale prediction head at the detection stage of the model. With the auto anchor feature, the model is able to adjust the anchor boxes dynamically during training, which can improve its overall performance. The SPPF layer divides the feature map into five pyramid levels, each corresponding to a different scale. This enables the model to detect objects of different sizes by pooling features from all pyramid levels. Extreme Small Scale prediction head is specifically designed for small object detection and uses anchor boxes with small sizes and feature re-sampling techniques to improve the accuracy of SSOD. We perform quantitative evaluations on the VOC and achieved 85.4% mAP, 79.8% precision, 80.3% recall, and 80% F1-score. These reliable results prove that the suggested model performs better than existing models in detecting small-scale objects.

A bearing fault diagnosis method based on M-SSCNN and M-LR attention mechanism

Bearing fault diagnosis is vital for mechanical maintenance and fault prediction. It ensures equipment safety, extends lifespan, reduces maintenance costs, and improves production efficiency. Nevertheless, it should be acknowledged that some existing diagnostic methods have achieved high accuracy rates in certain scenarios. However, the challenge lies in their limited generalization capabilities, which can lead to reduced accuracy when applied to diverse or unseen conditions. In this study, we proposed a new bearing fault diagnosis method to address the issue of low accuracy caused by the inadequate generalization of models in the process of rolling bearing fault diagnosis. The method is based on a multi-scale sliding convolution neural network and multi-level residual attention mechanism, the model exhibits high accuracy, strong generalization capability, and lightweight structure. Firstly, the time domain signal of the bearing vibration is converted into a two-dimensional time–frequency map, and the image is pixel-segmented using superpixel segmentation techniques. Next, a multi-scale parallel convolution approach is used to extract features to improve the adaptability and robustness of the model to objects of different sizes and scales. Sliding convolution is used instead of pooling to avoid the problem of feature loss caused by maximum pooling and average pooling. A multi-level attention mechanism is then introduced for all stacked channels to focus on the more important and critical information of the module, and residual connections are added to prevent degradation of the network performance. Finally, the proposed method is passed through the fully connected layer for classification using the Softmax classifier. Experimental verification using public datasets and experimental data of our research group shows that the proposed method has better performance than the existing diagnostic methods and diagnostic models. The proposed method offers an advanced and innovative solution in the domain of bearing fault diagnosis.

Highly compact adaptive network based on transformer for RGBT tracking

RGBT tracking is a challenging task that requires robust fusion of visible images (RGB) and thermal infrared images (TIR) to handle various scenarios, such as illumination changes, occlusions, and camouflage. The current popular RGBT trackers mostly based on two stream Siamese trackers. They tend to separately extracts template and search images region features, which neglects relationship between target and background. Moreover, they do not fuse RGB and TIR features properly, limiting their ability to utilize complementary features. To address these issues, we introduce a highly compact adaptive transformer-based network that unifies the process of feature extracting and correlation between template and search images. In this way, the compact network has dual-branches. They can combine feature extraction and correlation for different modalities of template images and search images. Meanwhile, we introduce a cross-modal weight redistribution module (CMWR) for multi-modal fusion. This adaptive fusion scheme learns discriminative features of RGB and TIR data and assigns weights to them, enabling them to complement each other. Furthermore, to address the issue of tracking targets of different scales, we design scale-adaptive optimization pyramid module (SAOP) that adapt to objects of different sizes. Our method achieves exceptional performance on the GTOT, RGBT234 and LasHeR datasets, surpassing most of the existing methods. The results are consistent across multiple datasets, demonstrating the effectiveness and superiority of our approach. And our code is released at: https://github.com/ELOESZHANG/HCANet.

Mask2Former with Improved Query for Semantic Segmentation in Remote-Sensing Images

Semantic segmentation of remote sensing (RS) images is vital in various practical applications, including urban construction planning, natural disaster monitoring, and land resources investigation. However, RS images are captured by airplanes or satellites at high altitudes and long distances, resulting in ground objects of the same category being scattered in various corners of the image. Moreover, objects of different sizes appear simultaneously in RS images. For example, some objects occupy a large area in urban scenes, while others only have small regions. Technically, the above two universal situations pose significant challenges to the segmentation with a high quality for RS images. Based on these observations, this paper proposes a Mask2Former with an improved query (IQ2Former) for this task. The fundamental motivation behind the IQ2Former is to enhance the capability of the query of Mask2Former by exploiting the characteristics of RS images well. First, we propose the Query Scenario Module (QSM), which aims to learn and group the queries from feature maps, allowing the selection of distinct scenarios such as the urban and rural areas, building clusters, and parking lots. Second, we design the query position module (QPM), which is developed to assign the image position information to each query without increasing the number of parameters, thereby enhancing the model’s sensitivity to small targets in complex scenarios. Finally, we propose the query attention module (QAM), which is constructed to leverage the characteristics of query attention to extract valuable features from the preceding queries. Being positioned between the duplicated transformer decoder layers, QAM ensures the comprehensive utilization of the supervisory information and the exploitation of those fine-grained details. Architecturally, the QSM, QPM, and QAM as well as an end-to-end model are assembled to achieve high-quality semantic segmentation. In comparison to the classical or state-of-the-art models (FCN, PSPNet, DeepLabV3+, OCRNet, UPerNet, MaskFormer, Mask2Former), IQ2Former has demonstrated exceptional performance across three publicly challenging remote-sensing image datasets, 83.59 mIoU on the Vaihingen dataset, 87.89 mIoU on Potsdam dataset, and 56.31 mIoU on LoveDA dataset. Additionally, overall accuracy, ablation experiment, and visualization segmentation results all indicate IQ2Former validity.

INTEGRATED RESEARCH TOOLS IN URBAN AND SPATIAL PLANNING

In working with urban projects, we are usually faced with the need to study the design object, regardless of its scale, significance and value in the city and the functions it performs. The larger the scale of the research object, the more voluminous our research becomes and, accordingly, requires a clear division into different layers and gradation in order of importance to simplify the conduct of the research itself and the ability to predict the expected results. A classic way of analyzing large territorial, urban and spatial objects is a comprehensive urban planning analysis. However, today's urban and spatial studies go beyond urban planning analysis and require a synthesis with the methods of other social and humanitarian disciplines, going beyond mono-discipline into multidisciplinarity and complexity. Also, changes in values in urban and spatial design, when attention is focused on reuse, mixed use, programmatic design, sustainability and consideration of climate change, the importance of public spaces in the life of the city led to the use of another format of urban studies. For urban objects of different sizes, such as a fragment of the city within the boundaries of the streets, a block, a combination of blocks, an undeveloped part of the city, a post-industrial area that is being revitalized, the author has created a list of seven layers necessary for analysis, which include physical, morphological, social and historical and cultural aspects of the study: 1) territory in the structure of the city, 2) functions and content, 3) accessibility and mobility, 4) morphology and buildings development, 5) inhabitants and stakeholders, 6) open spaces, 7) history and identity. The characteristic features of this urban planning and spatial analysis are, firstly, a proposal at all levels of analysis to fix proposals for changes that will be detailed at the design phase. Secondly, at each layer of research, it is suggested to interact with residents and users and capture their feedback for each layer of analysis. These layers of analytical urban research can be supplemented depending on the complexity and specificity of the research object. And also depending on the direction and requests of the research, the expected results.

Multimodal Sensors Enabled Autonomous Soft Robotic System with Self-Adaptive Manipulation.

Human hands are amazingly skilled at recognizing and handling objects of different sizes and shapes. To date, soft robots rarely demonstrate autonomy equivalent to that of humans for fine perception and dexterous operation. Here, an intelligent soft robotic system with autonomous operation and multimodal perception ability is developed by integrating capacitive sensors with triboelectric sensor. With distributed multiple sensors, our robot system can not only sense and memorize multimodal information but also enable an adaptive grasping method for robotic positioning and grasp control, during which the multimodal sensory information can be captured sensitively and fused at feature level for crossmodally recognizing objects, leading to a highly enhanced recognition capability. The proposed system, combining the performance and physical intelligence of biological systems (i.e., self-adaptive behavior and multimodal perception), will greatly advance the integration of soft actuators and robotics in many fields.

A low-cost underactuated compliant gripper with multifunctional jaws for precision manipulation

Precision manipulation tasks often require the use of compliant grippers to handle small and delicate objects accurately. This paper proposes a novel low-cost underactuated compliant gripper with integrated position and force sensors for precision manipulation. The gripper has a millimeter-scale grasping range and can adapt to objects of varying sizes and shapes. This is made possible by a flexure motion transmission mechanism that can undergo significant deformation, an underactuated seesaw flexure mechanism, and a pair of multifunctional jaws. Analytical models based on the pseudo-rigid-body approach are developed to analyze the kinematic, static, and dynamic characteristics of the gripper design. Finite element simulations are conducted to investigate the static and dynamic performance of the gripper. The gripper prototype is fabricated using 3D printing technology for a series of experimental tests. The results of these experiments demonstrate that the developed gripper has excellent motion tracking capabilities and high motion and force resolutions, enabling precise and accurate manipulation tasks. Furthermore, the gripper is capable of successfully grasping objects of different sizes and shapes through parallel and enveloping grasps.

Electrical Stimulation of Regenerative Peripheral Nerve Interfaces (RPNIs) Induces Referred Sensations in People With Upper Limb Loss.

Individuals with upper limb loss lack sensation of the missing hand, which can negatively impact their daily function. Several groups have attempted to restore this sensation through electrical stimulation of residual nerves. The purpose of this study was to explore the utility of regenerative peripheral nerve interfaces (RPNIs) in eliciting referred sensation. In four participants with upper limb loss, we characterized the quality and location of sensation elicited through electrical stimulation of RPNIs over time. We also measured functional stimulation ranges (sensory perception and discomfort thresholds), sensitivity to changes in stimulation amplitude, and ability to differentiate objects of different stiffness and sizes. Over a period of up to 54 months, stimulation of RPNIs elicited sensations that were consistent in quality (e.g. tingling, kinesthesia) and were perceived in the missing hand and forearm. The location of elicited sensation was partially-stable to stable in 13 of 14 RPNIs. For 5 of 7 RPNIs tested, participants demonstrated a sensitivity to changes in stimulation amplitude, with an average just noticeable difference of 45 nC. In a case study, one participant was provided RPNI stimulation proportional to prosthetic grip force. She identified four objects of different sizes and stiffness with 56% accuracy with stimulation alone and 100% accuracy when stimulation was combined with visual feedback of hand position. Collectively, these experiments suggest that RPNIs have the potential to be used in future bi-directional prosthetic systems.

Camouflaged Object Segmentation Based on Matching-Recognition-Refinement Network.

In the biosphere, camouflaged objects take the advantage of visional wholeness by keeping the color and texture of the objects highly consistent with the background, thereby confusing the visual mechanism of other creatures and achieving a concealed effect. This is also the main reason why the task of camouflaged object detection is challenging. In this article, we break the visual wholeness and see through the camouflage from the perspective of matching the appropriate field of view. We propose a matching-recognition-refinement network (MRR-Net), which consists of two key modules, i.e., the visual field matching and recognition module (VFMRM) and the stepwise refinement module (SWRM). In the VFMRM, various feature receptive fields are used to match candidate areas of camouflaged objects of different sizes and shapes and adaptively activate and recognize the approximate area of the real camouflaged object. The SWRM then uses the features extracted by the backbone to gradually refine the camouflaged region obtained by VFMRM, thus yielding the complete camouflaged object. In addition, a more efficient deep supervision method is exploited, making the features from the backbone input into the SWRM more critical and not redundant. Extensive experimental results demonstrate that our MRR-Net runs in real-time (82.6 frames/s) and significantly outperforms 30 state-of-the-art models on three challenging datasets under three standard metrics. Furthermore, MRR-Net is applied to four downstream tasks of camouflaged object segmentation (COS), and the results validate its practical application value. Our code is publicly available at: https://github.com/XinyuYanTJU/MRR-Net.

Performance research of C# programming language data serializers using the developed software product for testing

The article deals with the issue of using data serializers for the implementation of projects related to the processing of large volumes of data, as well as the support of high-speed data transmission in distributed systems. It is shown that in this context, the choice of the most effective serialization mechanism is critical for ensuring the performance and scalability of applications. The purpose of this work is to study the effectiveness of data serializers of the C# programming language by developing a software product for testing serializers using objects of different size and type. A review of scientific research on the use of various data serialization formats: XML, JSON, BSON, MessagePack, Smile, Protocol Buffers, Flat Buffers, Apache Thrift was conducted. It was concluded that XML and JSON formats are the most popular today, and their comparative analysis was performed. The expediency of using the JSON serialization format is substantiated, which is due to its safety compared to the binary format, its smaller size compared to the XML format, as well as the support of most software development tools. The .NET framework is chosen, which provides standard tools for JSON serialization of the C# programming language, namely: System.Runtime.Serialize.Json and System.Text.Json, which are supplied by default. The most popular software solutions for serializing C# objects are analyzed, the feasibility of testing such serializers as Jil, Json.NET, Utf8Json, SpanJson and standard serializers is shown in order to identify the advantages and disadvantages of their use for the implementation of specific tasks and projects. The C# BenchmarkDotNet programming language library was chosen to create the tester program. It is noted that this framework of the .NET platform allows you to convert methods into tests and create performance testing thanks to a powerful statistical mechanism. A class diagram and a component diagram of the developed software are given. A study of 5 data serializers was conducted, which included the execution of 7 experiments on serialization of objects with different types of data. The consumption of time and working memory during serialization of small and large objects was analyzed; objects containing one-dimensional, two-dimensional and three-dimensional arrays of natural numbers, an object with a complex chain of class inheritance, as well as an object containing a dictionary. The results of experimental studies showed the dependence of the effectiveness of serializers on the type and volume of data to be serialized. It is concluded that there is no one-size-fits-all serializer that will perform best in all cases. Recommendations for the use of various serializers are provided, taking into account the requirements of a specific project

A Fast Attention-Guided Hierarchical Decoding Network for Real-Time Semantic Segmentation.

Semantic segmentation provides accurate scene understanding and decision support for many applications. However, many models strive for high accuracy by adopting complex structures, decreasing the inference speed, and making it challenging to meet real-time requirements. Therefore, a fast attention-guided hierarchical decoding network for real-time semantic segmentation (FAHDNet), which is an asymmetric U-shaped structure, is proposed to address this issue. In the encoder, we design a multi-scale bottleneck residual unit (MBRU), which combines the attention mechanism and decomposition convolution to design a parallel structure for aggregating multi-scale information, making the network perform better at processing information at different scales. In addition, we propose a spatial information compensation (SIC) module that effectively uses the original input to make up for the spatial texture information lost during downsampling. In the decoder, the global attention (GA) module is used to process the feature map of the encoder, enhance the feature interaction in the channel and spatial dimensions, and enhance the ability to mine feature information. At the same time, the lightweight hierarchical decoder integrates multi-scale features to better adapt to different scale targets and accurately segment objects of different sizes. Through experiments, FAHDNet performs outstandingly on two public datasets, Cityscapes and Camvid. Specifically, the network achieves 70.6% mean intersection over union (mIoU) at 135 frames per second (FPS) on Cityscapes and 67.2% mIoU at 335 FPS on Camvid. Compared to the existing networks, our model maintains accuracy while achieving faster inference speeds, thus enhancing its practical usability.

Human-Robot Interaction Using Learning from Demonstrations and a Wearable Glove with Multiple Sensors.

Human-robot interaction is of the utmost importance as it enables seamless collaboration and communication between humans and robots, leading to enhanced productivity and efficiency. It involves gathering data from humans, transmitting the data to a robot for execution, and providing feedback to the human. To perform complex tasks, such as robotic grasping and manipulation, which require both human intelligence and robotic capabilities, effective interaction modes are required. To address this issue, we use a wearable glove to collect relevant data from a human demonstrator for improved human-robot interaction. Accelerometer, pressure, and flexi sensors were embedded in the wearable glove to measure motion and force information for handling objects of different sizes, materials, and conditions. A machine learning algorithm is proposed to recognize grasp orientation and position, based on the multi-sensor fusion method.

Improved Object Detection Method Utilizing YOLOv7-Tiny for Unmanned Aerial Vehicle Photographic Imagery

In unmanned aerial vehicle photographs, object detection algorithms encounter challenges in enhancing both speed and accuracy for objects of different sizes, primarily due to complex backgrounds and small objects. This study introduces the PDWT-YOLO algorithm, based on the YOLOv7-tiny model, to improve the effectiveness of object detection across all sizes. The proposed method enhances the detection of small objects by incorporating a dedicated small-object detection layer, while reducing the conflict between classification and regression tasks through the replacement of the YOLOv7-tiny model’s detection head (IDetect) with a decoupled head. Moreover, network convergence is accelerated, and regression accuracy is improved by replacing the Complete Intersection over Union (CIoU) loss function with a Wise Intersection over Union (WIoU) focusing mechanism in the loss function. To assess the proposed model’s effectiveness, it was trained and tested on the VisDrone-2019 dataset comprising images captured by various drones across diverse scenarios, weather conditions, and lighting conditions. The experiments show that mAP@0.5:0.95 and mAP@0.5 increased by 5% and 6.7%, respectively, with acceptable running speed compared with the original YOLOv7-tiny model. Furthermore, this method shows improvement over other datasets, confirming that PDWT-YOLO is effective for multiscale object detection.

MSER-Vertical Sobel for Vehicle Logo Detection

Detecting a vehicle logo is the first step before realizing the identity of the logo. However, the detection of logos can pose difficulties due to various factors, including logo variations, differing scales and orientations, background interference, varying lighting conditions, and partial obstruction. This paper presents a vehicle logo detection method using hand-crafted features. We used a combination of Maximally Stable Extremal Region (MSER) and Vertical Sobel. We combine vertical Sobel with MSER to overcome MSER's limitation in recognizing objects of different sizes. These two features are merged using a closing morphology operation to form blobs selected as logo candidate areas. Moreover, a Support Vector Machine (SVM) is implemented to choose a logo area by analyzing each candidate's Histogram of Oriented Gradient (HOG). The proposed method was compared with other methods by implementing them on the same dataset. The significant advantage of using MSER-Vertical Sobel is its fast computation time. It is faster than other approaches that use non-handcrafted features. The test results show that the MSER-Vertical Sobel can achieve high accuracy and the fastest computation time.