An Approach for Construct Semantic Map with Scene Classification and Object Semantic Segmentation

Abstract. Semantic information in images—such as meaningful, recognizable regions or objects that are incongruent with the overall scene—can effectively capture attention. The meaning map is currently the primary method for mapping the distribution of semantic information across visual stimuli. However, this approach relies on subjective human ratings of semantic meaningfulness and requires extensive manual annotation for each image prior to analysis. To address these limitations and enable rapid, efficient, and reproducible generation of semantic distribution maps for any given image, this paper proposes an automated method for constructing semantic information maps using multimodal large language models (MLLMs). Our approach generates two types of semantic maps: local semantic information maps, which quantify the semantic content at each spatial location within an image, and global semantic maps, which assess the contextual relevance of local regions to the overall scene. Additionally, the method can generate distribution maps of visual information associated with specific concepts. We argue that this method significantly enhances the precision and flexibility in controlling, measuring, and manipulating semantic information in visual stimuli, thereby advancing research in visual attention and visual language processing. The method is currently under further refinement.

With the increasingly complex application scenarios of indoor mobile robots, traditional navigation methods based on metric maps have been unable to meet people's needs. Mobile robots not only need to perceive the spatial geometric information of the environment, but also need to deeply and comprehensively understand the semantic information of the environment in order to perform tasks such as complex behavioral decision-making and human-computer interaction. In this paper, we propose a semantic mapping system for indoor environments based on a monocular camera and a laser. The semantic mapping system adopts the technique of scene classification to construct the scene semantics of indoor environments, in which the semantic classifier is embedded into a recurrent neural network to better learn the correlation of consecutive frames. Experimental results indicate that the proposed semantic mapping system exhibits great performance in the robustness and accuracy of semantic mapping.

Semantic mapping based on the supervised object detectors is sensitive to image distribution. In real-world environments, the object detection and segmentation performance can lead to a major drop, preventing the use of semantic mapping in a wider domain. On the other hand, the development of vision-language foundation models demonstrates a strong zero-shot transferability across data distribution. It provides an opportunity to construct generalizable instance-aware semantic maps. Hence, this work explores how to boost instance-aware semantic mapping from object detection generated from foundation models. We propose a probabilistic label fusion method to predict close-set semantic classes from open-set label measurements. An instance refinement module merges the over-segmented instances caused by inconsistent segmentation. We integrate all the modules into a unified semantic mapping system. Reading a sequence of RGB-D input, our work incrementally reconstructs an instance-aware semantic map. We evaluate the zero-shot performance of our method in ScanNet and SceneNN datasets. Our method achieves 40.3 mean average precision (mAP) on the ScanNet semantic instance segmentation task. It outperforms the traditional semantic mapping method significantly.

Nowadays, Intelligent Transportation System (ITS) has become one of the most popular subjects of scientific research. ITS provides innovative services to transport and traffic monitoring like vehicle segmentation and classification. Image understanding and object semantic segmentation in traffic scenes is a very important topic in the trend of autonomous driving issues, like autonomous vehicles and robotics. Actually, Deep Convolution Neural Network (CNN) architectures have given very good results and good performance in computer vision tasks such as classification, object detection, and segmentation. In this scope, we can distinguish two modes of CNN training, the pre-trained model and the training from scratch. In fact, deep neural network training without pre-trained weights and little data requires more training iterations. Besides, deeper models are more efficient than their shallow counterparts for the task of semantic segmentation. In this paper, we will make a comparative study between many deep CNNs models that can train the CNN model from scratch on small datasets, in addition, we will use data augmentation techniques. Extensive experiments were performed on the MiniCity urban scene dataset to prove the effectiveness of the used neural networks while obtaining promising results.

Object detection algorithms using convolutional neural networks (CNNs) achieve high detection accuracy, but it is challenging to realize real-time object detection due to their high computational complexity, especially on resource-constrained mobile platforms. In this article, we propose an algorithm-hardware co-optimization approach to designing a real-time object detection system. We first develop a compact object detection model based on a binarized neural network (BNN), which employs a new layer structure, the DenseToRes layer, to mitigate information loss due to deep quantization. We also propose an efficient object detection processor that runs object detection with high throughput using limited hardware rescources. We develop a resource-efficient processing unit supporting variable precision with minimal hardware overheads. Implemented in field-programmable gate array (FPGA), the object detection processor achieves 64.51 frames/s throughput with 64.92 mean average precision (mAP) accuracy. Compared to prior FPGA-based designs for object detection, our design achieves high throughput with competitive accuracy and lower hardware implementation costs.

This research proposes a novel hardware-optimized design to accelerate Convolutional Neural Networks (CNNs) using Verilog HDL. The design is specifically developed for the DARKNET-19 system model, which serves as the backbone of the YOLOv3-tiny algorithm, a widely used framework for real-time object detection in dynamic environments. The CNN architecture was implemented in Verilog HDL and synthesized using Synopsys Design Compiler, with a focus on improving both object detection accuracy and hardware resource efficiency. The proposed design efficiently performs key CNN operations, including convolution, pooling, and activation, enabling faster real-time object detection compared to many existing methods. To improve performance, the hardware design incorporates parallel processing techniques, allowing multiple computations to be executed simultaneously. This significantly reduces the system latency and power consumption. The convolutional layers of the DARKNET-19 architecture are efficiently mapped onto the hardware platform, ensuring optimized data storage and fast memory access, which further enhances processing speed and detection accuracy. An innovative feature of the design is a 2-dimensional image preprocessing module that prepares input images before they are fed into the CNN. This preprocessing stage includes image resizing, brightness normalization, and color adjustment, which helps the CNN process visual data more effectively. After preprocessing, the images pass through several CNN layers. The convolutional layers extract key features from the images, while the pooling and activation layers refine these features to improve detection performance. Finally, the processed data is analyzed by the YOLOv3-tiny algorithm, which identifies and locates objects in the images with high precision. Experimental results demonstrate that the proposed high-speed and resource-efficient hardware architecture is well-suited for real-time object detection applications, particularly in highly dynamic and unpredictable environments.

The robot simultaneous localization and mapping (SLAM) is a very important and useful technology in the robotic field. However, the environmental map constructed by the traditional visual SLAM method contains little semantic information, which cannot satisfy the needs of complex applications. The semantic map can deal with this problem efficiently, which has become a research hot spot. This paper proposed an improved deep residual network- (ResNet-) based semantic SLAM method for monocular vision robots. In the proposed approach, an improved image matching algorithm based on feature points is presented, to enhance the anti-interference ability of the algorithm. Then, the robust feature point extraction method is adopted in the front-end module of the SLAM system, which can effectively reduce the probability of camera tracking loss. In addition, the improved key frame insertion method is introduced in the visual SLAM system to enhance the stability of the system during the turning and moving of the robot. Furthermore, an improved ResNet model is proposed to extract the semantic information of the environment to complete the construction of the semantic map of the environment. Finally, various experiments are conducted and the results show that the proposed method is effective.

Remote sensing image (RSI) scene classification is the foundation and important technology of ground object detection, land use management and geographic analysis. During recent years, convolutional neural networks (CNNs) have achieved significant success and are widely applied in RSI scene classification. However, crafted images that serve as adversarial examples can potentially fool CNNs with high confidence and are hard for human eyes to interpret. For the increasing security and robust requirements of RSI scene classification, the adversarial example problem poses a serious problem for the classification results derived from systems using CNN models, which has not been fully recognized by previous research. In this study, to explore the properties of adversarial examples of RSI scene classification, we create different scenarios by testing two major attack algorithms (i.e., the fast gradient sign method (FGSM) and basic iterative method (BIM)) trained on different RSI benchmark datasets to fool CNNs (i.e., InceptionV1, ResNet and a simple CNN). In the experiment, our results show that CNNs of RSI scene classification are also vulnerable to adversarial examples, and some of them have a fooling rate of over 80%. These adversarial examples are affected by the architecture of CNNs and the type of RSI dataset. InceptionV1 has a fooling rate of less than 5%, which is lower than the others. Adversarial examples generated on the UCM dataset are easier than other datasets. Importantly, we also find that the classes of adversarial examples have an attack selectivity property. Misclassifications of adversarial examples of RSIs are related to the similarity of the original classes in the CNN feature space. Attack selectivity reveals potential classes of adversarial examples and provides insights into the design of defensive algorithms in future research.

Currently, artificial intelligence (AI) technology offers opportunities to address serious challenges in waste management in the fashion industry. This study systematically reviewed and analyzed literature on AI applications in textile waste management from 2014 to 2024. We aimed to review the intervention effects of AI technologies on textile waste across stages of the fashion industry lifecycle and explore AI’s role in promoting circular supply chains (CSCs). The results show that AI plays a prominent role in four key areas: Enhanced intelligent analysis of market dynamics, optimizing consumer experience-oriented durability design, collaboratively optimizing production processes and inventory management, and advancement of intelligent waste management. Convolutional neural networks are the most widely used AI technology due to their strength in image recognition. However, AI technologies also face limitations such as high data requirements. Future research should attempt to promote improvements in policies, enterprise, and technologies to unleash greater potential for AI in CSCs.

Cloud computing infrastructures have become the de-facto platform for data driven machine learning applications. However, these centralized models of computing are unqualified for dispersed high-volume real-time edge data intensive applications such as real time object detection, where video streams may be captured at multiple geographical locations. While many recent advancements in object detection have been made using Convolutional Neural Networks, these performance improvements only focus on a single, contiguous object detection model. In this paper, we propose a distributed Edge-Cloud R-CNN pipeline. By splitting the object detection pipeline into components and dynamically distributing these components in the cloud, we can achieve optimal performance to enable real time object detection. As a proof of concept, we evaluate the performance of the proposed system on a distributed computing platform including cloud servers and edge-embedded devices for real-time object detection on live video streams.

[ACCESS RESTRICTED TO THE UNIVERSITY OF MISSOURI AT REQUEST OF AUTHOR.] Camera traps are a popular tool to sample animal populations because they are noninvasive, detect a variety of species, and can record many thousands of animal detections per deployment. Cameras are typically set to take bursts of multiple images for each detection, and are deployed in arrays of dozens or hundreds of sites, often resulting in millions of images per study. The task of converting images to animal detection records from such large image collections is daunting, and made worse by situations that generate copious empty pictures from false triggers (e.g. camera malfunction or moving vegetation) or pictures of humans. We offer the first widely available computer vision tool for processing camera trap images. Our results show that the tool is accurate and results in substantial time savings for processing large image datasets, thus improving our ability to monitor wildlife across large scales with camera traps. In this dissertation, we have developed new image/video processing and computer vision algorithms for efficient and accurate object detection and sequence-level classiffication from natural scene camera-trap images. This work addresses the following five major tasks: (1) Human-animal detection. We develop a fast and accurate scheme for human-animal detection from highly cluttered camera-trap images using joint background modeling and deep learning classification. Specifically, first, We develop an effective background modeling and subtraction scheme to generate region proposals for the foreground objects. We then develop a cross-frame image patch verification to reduce the number of foreground object proposals. Finally, We perform complexity-accuracy analysis of deep convolutional neural networks (DCNN) to develop a fast deep learning classification scheme to classify these region proposals into three categories: human, animals, and background patches. The optimized DCNN is able to maintain high level of accuracy while reducing the computational complexity by 14 times. Our experimental results demonstrate that the proposed method outperforms existing methods on the camera-trap dataset. (2) Object segmentation from natural scene. We first design and train a fast DCNN for animal-human-background object classification, which is used to analyze the input image to generate multi-layer feature maps, representing the responses of different image regions to the animal-human-background classifier. From these feature maps, we construct the so-called deep objectness graph for accurate animal-human object segmentation with graph cut. The segmented object regions from each image in the sequence are then verfied and fused in the temporal domain using background modeling. Our experimental results demonstrate that our proposed method outperforms existing state-of-the-art methods on the camera-trap dataset with highly cluttered natural scenes. (3) DCNN domain background modeling. We replaced the background model with a new more efficient deep learning based model. The input frames are segmented into regions through the deep objectness graph then the region boundaries of the input frames are multiplied by each other to obtain the regions of movement patches. We construct the background representation using the temporal information of the co-located patches. We propose to fuse the subtraction and foreground/background pixel classiffcation of two representation : a) chromaticity and b) deep pixel information. (4) Sequence-level object classiffcation. We proposed a new method for sequence-level video recognition with application to animal species recognition from camera trap images. First, using background modeling and cross-frame patch verification, we developed a scheme to generate candidate object regions or object proposals in the spatiotemporal domain. Second, we develop a dynamic programming optimization approach to identify the best temporal subset of object proposals. Third, we aggregate and fuse the features of these selected object proposals for efficient sequence-level animal species classification.

Computational visual perception, also known as computer vision, is a field of artificial intelligence that enables computers to process digital images and videos in a similar way as biological vision does. It involves methods to be developed to replicate the capabilities of biological vision. The computer vision’s goal is to surpass the capabilities of biological vision in extracting useful information from visual data. The massive data generated today is one of the driving factors for the tremendous growth of computer vision. This survey incorporates an overview of existing applications of deep learning in computational visual perception. The survey explores various deep learning techniques adapted to solve computer vision problems using deep convolutional neural networks and deep generative adversarial networks. The pitfalls of deep learning and their solutions are briefly discussed. The solutions discussed were dropout and augmentation. The results show that there is a significant improvement in the accuracy using dropout and data augmentation. Deep convolutional neural networks’ applications, namely, image classification, localization and detection, document analysis, and speech recognition, are discussed in detail. In‐depth analysis of deep generative adversarial network applications, namely, image‐to‐image translation, image denoising, face aging, and facial attribute editing, is done. The deep generative adversarial network is unsupervised learning, but adding a certain number of labels in practical applications can improve its generating ability. However, it is challenging to acquire many data labels, but a small number of data labels can be acquired. Therefore, combining semisupervised learning and generative adversarial networks is one of the future directions. This article surveys the recent developments in this direction and provides a critical review of the related significant aspects, investigates the current opportunities and future challenges in all the emerging domains, and discusses the current opportunities in many emerging fields such as handwriting recognition, semantic mapping, webcam‐based eye trackers, lumen center detection, query‐by‐string word, intermittently closed and open lakes and lagoons, and landslides.

— In today's era, the challenge of object detection within laboratory spaces is paramount. The need for automated monitoring systems supporting object detection within laboratory settings, particularly for service robots, is crucial for scientific research and safety. Utilizing convolutional artificial neural networks has shown promising capabilities in object recognition. This paper proposes a novel method for detecting and localizing specific objects within laboratory environments using deep learning techniques. Employing a lightweight primary feature extractor allows for the identification of crucial object features without imposing excessive computational demands. Additionally, a depthwise separable convolution module is introduced, designed to capture essential components within multi-level convolutional patches specific to laboratory conditions. To address the challenges encountered within laboratory spaces, a new dataset is proposed, encompassing issues such as lighting variations, blurriness, occlusions, and complex backgrounds. Evaluation results indicate that the proposed model surpasses other lightweight object detection models in laboratory settings, offering high accuracy and efficiency. This model can be efficiently implemented on low-tier devices, ensuring real-time object detection and processing within laboratory environments. Keywords — object detection, service robot, convolutional neural networks, You Only Look Once version 5. Abstrak — Di era sekarang ini, tantangan deteksi objek di dalam ruang laboratorium menjadi sangat penting. Kebutuhan akan sistem pemantauan otomatis yang mendukung deteksi objek di dalam laboratorium, khususnya untuk robot servis, sangat penting untuk penelitian ilmiah dan keselamatan. Memanfaatkan jaringan saraf tiruan convolutional telah menunjukkan kemampuan yang menjanjikan dalam pengenalan objek. Makalah ini mengusulkan metode baru untuk mendeteksi dan melokalisasi objek tertentu di dalam lingkungan laboratorium menggunakan teknik pembelajaran mendalam. Menggunakan ekstraktor fitur utama yang ringan memungkinkan identifikasi fitur objek yang penting tanpa membebani komputasi yang berlebihan. Selain itu, modul konvolusi yang dapat dipisahkan secara mendalam juga diperkenalkan, yang dirancang untuk menangkap komponen penting dalam patch konvolusi multi-level yang spesifik untuk kondisi laboratorium. Untuk mengatasi tantangan yang dihadapi di dalam ruang laboratorium, dataset baru diusulkan, yang mencakup masalah seperti variasi pencahayaan, kekaburan, oklusi, dan latar belakang yang kompleks. Hasil evaluasi menunjukkan bahwa model yang diusulkan melampaui model pendeteksian objek ringan lainnya di lingkungan laboratorium, menawarkan akurasi dan efisiensi yang tinggi. Model ini dapat diimplementasikan secara efisien pada perangkat tingkat rendah, memastikan pendeteksian dan pemrosesan objek secara real-time di lingkungan laboratorium. Kata kunci — deteksi objek, robot layanan, jaringan saraf konvolusi, Anda Hanya Melihat Sekali versi 5.

Scene classification of high resolution remote sensing images plays an important role for a wide range of applications. While significant efforts have been made in developing various methods for scene classification, most of them are based on handcrafted or shallow learning-based features. In this paper, we investigate the use of deep convolutional neural network (CNN) for scene classification. To this end, we first adopt two simple and effective strategies to extract CNN features: (1) using pre-trained CNN models as universal feature extractors, and (2) domain-specifically fine-tuning pre-trained CNN models on our scene classification dataset. Then, scene classification is carried out by using simple classifiers such as linear support vector machine (SVM). In our work, three off-the-shelf CNN models including AlexNet [1], VGGNet [2], and GoogleNet [3] are investigated. Comprehensive evaluations on a publicly available 21 classes land use dataset and comparisons with several state-of-the-art approaches demonstrate that deep CNN features are effective for scene classification of high resolution remote sensing images.

Object detection is not only shaping how Computers see and analyze things but it is also helping in the behavior of how an object reacts to the change in its environment. The main application of these object detection sensors or software is to find the location of an object in space or to track its movement. Object detection has infinitely many use cases and in this paper, we are introducing an application that will allow safety of users struck in a disaster and who need to be evacuated. In such cases the main thing to focus and to eradicate is camera noise, saturation and image compression. Our solution is to establish a connection between the person struck in a disaster with fire safety people. This works over a convolutional network that allows us to detect vulnerable things present inside a room that needs to be rescued and can also give an insight of any explosive inside the room. Our model uses Faster-RCNN and COCO which is a pretrained dataset. This allows real time object detection and classification on our network. Using this we were able to detect an object or a person and get him to rescue by providing them a shortest way out of that place. With this we were able to get an accuracy of more than 75% in our object detection model.