The Multiplicative Path Toward Prior-Shape Guided Active Contour for Object Detection

Weakly supervised easy-to-hard learning for object detection in image sequences

This paper proposes a method for estimating 3D information, such as shape, orientation, size, and position of objects in a monocular image, and reproduce scenes in 3D point clouds using Convolutional Neural Network (CNN). This study proposes a network that combines depth estimation, object detection, and point cloud estimation to estimate 3D information of objects. The proposed network requires networks for object detection and segmentation, and a point cloud estimation for object shape estimation. The point cloud estimation network is robust to the reproduction of the object's surface and can deal with unknown objects through a semantic understanding of the object’s shape. In addition to these networks, we combine a depth estimation network for estimating the depth of the entire scene and the distance between the camera and object. In this paper, we consider the point cloud estimation network. We estimate the point clouds for real objects in the images of the dataset and evaluate the output point clouds.

Low-light object detection involves identifying and locating objects in images captured under poor lighting conditions. It plays a significant role in surveillance and security, night pedestrian recognition, and autonomous driving, showcasing broad application prospects. Most existing object detection algorithms and datasets are designed for normal lighting conditions, leading to a significant drop in detection performance when applied to low-light environments. To address this issue, we propose a Low-Light Detection with Low-Light Enhancement (LDWLE) framework. LDWLE is an encoder-decoder architecture where the encoder transforms the raw input data into a compact, abstract representation (encoding), and the decoder gradually generates the target output format from the representation produced by the encoder. Specifically, during training, low-light images are input into the encoder, which produces feature representations that are decoded by two separate decoders: an object detection decoder and a low-light image enhancement decoder. Both decoders share the same encoder and are trained jointly. Throughout the training process, the two decoders optimize each other, guiding the low-light image enhancement towards improvements that benefit object detection. If the input image is normally lit, it first passes through a low-light image conversion module to be transformed into a low-light image before being fed into the encoder. If the input image is already a low-light image, it is directly input into the encoder. During the testing phase, the model can be evaluated in the same way as a standard object detection algorithm. Compared to existing object detection algorithms, LDWLE can train a low-light robust object detection model using standard, normally lit object detection datasets. Additionally, LDWLE is a versatile training framework that can be implemented on most one-stage object detection algorithms. These algorithms typically consist of three components: the backbone, neck, and head. In this framework, the backbone functions as the encoder, while the neck and head form the object detection decoder. Extensive experiments on the COCO, VOC, and ExDark datasets have demonstrated the effectiveness of LDWLE in low-light object detection. In quantitative measurements, it achieves an AP of 25.5 and 38.4 on the synthetic datasets COCO-d and VOC-d, respectively, and achieves the best AP of 30.5 on the real-world dataset ExDark. In qualitative measurements, LDWLE can accurately detect most objects on both public real-world low-light datasets and self-collected ones, demonstrating strong adaptability to varying lighting conditions and multi-scale objects.

The area, object detection has seen a drastic development of algorithms and techniques over the past years. The arrival of deep learning has boosted the improvement in accuracy and performance of systems. This paper is a brief survey of several works developed so far in the field of image classification and object detection and a relative study of different methods. Survey is divided in three sub areas as Machine Learning based approach, Deep Learning based approach and object detection for night vision applications. A comparative table with the discussed works is also given.

Being able to segment the esophagus without user interaction from 3-D CT data is of high value to radiologists during oncological examinations of the mediastinum. The segmentation can serve as a guideline and prevent confusion with pathological tissue. However, limited contrast to surrounding structures and versatile shape and appearance make segmentation a challenging problem. This paper presents a multistep method. First, a detector that is trained to learn a discriminative model of the appearance is combined with an explicit model of the distribution of respiratory and esophageal air. In the next step, prior shape knowledge is incorporated using a Markov chain model. We follow a "detect and connect" approach to obtain the maximum a posteriori estimate of the approximate esophagus shape from hypothesis about the esophagus contour in axial image slices. Finally, the surface of this approximation is nonrigidly deformed to better fit the boundary of the organ. The method is compared to an alternative approach that uses a particle filter instead of a Markov chain to infer the approximate esophagus shape, to the performance of a human observer and also to state of the art methods, which are all semiautomatic. Cross-validation on 144 CT scans showed that the Markov chain based approach clearly outperforms the particle filter. It segments the esophagus with a mean error of 1.80 mm in less than 16 s on a standard PC. This is only 1 mm above the interobserver variability and can compete with the results of previously published semiautomatic methods.

Background/IntroductionThe left ventricle is vital for assessing heart function, and its analysis in echocardiographic images supports the diagnosis of many cardiac conditions. However, accurate segmentation is difficult due to image noise, low contrast, and anatomical variability. Using anatomical information and prior shape knowledge can improve the robustness and accuracy of segmentation, especially in challenging cases.PurposeDeep learning techniques are widely used for cardiac segmentation due to their strong performance in image analysis. This work aims to enhance segmentation robustness by integrating prior shape information directly into the network, allowing it to better handle challenging image conditions.MethodThis shape information can be obtained from deep statistical shape models (SSM) that capture the variability of shapes within a population as a statistical representation. We present a fusion-based segmentation approach that combines a state-of-the-art segmentation model with shape information from deep SMM. This shape information is incorporated into the training process through an additional loss term.In our method, we use U-Net for segmentation and employ Base-DeepSSM [2] (Fig. 1_b) and TL-DeepSSM [3] (Fig. 1_c) frameworks to extract shape information in the form of latent codes. These codes are generated using frozen encoders from pre-trained Base/TL-DeepSSM models. The added loss function (L_latent) measures the difference between the latent codes of the predicted segmentations and the original input images (Fig. 1_a). The proposed loss function helps maintain the anatomical shape in the predicted segmentation map. The final loss is the weighted sum of latent loss and dice loss.ResultsWe applied our proposed method to the Echocardiography Analysis (MITEA) dataset [1]. In each image, the endocardium and epicardium of the left ventricle are manually labeled, providing precise anatomical segmentation for training and evaluation. A selected subset of the data was divided into 54 image-label pairs for training (75%), 12 for validation (17%), and 14 for testing (8%). The training runs for a total of 60 epochs: the first 20 epochs train only the U-Net using Dice Loss, and the following 40 epochs include both Dice Loss and the latent loss.The proposed model achieved a highest validation Dice score of 0.84 and reached a Dice of 0.83 on the test dataset for epicardium, with a standard deviation of 0.07. In comparison, the baseline U-Net model obtained a validation Dice score of 0.81 and a test Dice of 0.80, with a higher standard deviation of 0.10. These results indicate that the fusion model offers improved segmentation accuracy and greater consistency over the standard U-Net.A promising direction for future work is to embed shape information directly into the network architecture, such as the U-Net’s encoder, instead of using it solely as an additional loss function.Block diagram of the proposed methodQualitative Results

The use of residual (multiple stage) vector quantizer codevectors in a nearest neighbor classifier for direct classification of image pixel data is proposed. This approach combines the successive approximation process generated by theresidual vector quantizer with sequential decision making. This approach potentially has the advantage of making large data base searches for small object or texture recognition in images both computation and memory efficient. Key Words: nearest neighbor classifier, vector quantization 1 INTRODUCTION The technical goals of counter-mine programs require that systems be developed for processing sensor data forautonomous detection and classification of mine-like objects in image data. The autonomous detection task involveslocal image decisions to discriminate between harmless and potentially hazardous subregions of an image. The au-tonomous classification task involves decisions to verify and identify potential threats. Machine-based identificationusing entire images can sometimes be achieved by very sophisticated, and often, computationally demanding algo-rithms. Machine-based classification using only small regions of an image to identify small objects is much simpler.The scope of this paper is restricted to the effective automation of the detection and classification of small objects( objects that are comprised on the order of 10 '

Object detection is one of the essential tasks in computer vision, with most detection methods relying on a limited number of sizes for anchor boxes. However, the boundaries of particular composite objects, such as ports, highways, and golf courses, are ambiguous in remote sensing images, and therefore, it is challenging for the anchor-based method to accommodate the substantial size variation of the objects. In addition, the dense placement of anchor boxes imbalances the positive and negative samples, which affects the end-to-end architecture of deep learning methods. Hence, this paper proposes a single-stage object detection model named Xnet to address this issue. The proposed method designs a deformable convolution backbone network used in the feature extraction stage. Compared to the standard convolution, it adds learnable parameters for dynamically analyzing the boundary and offset of the receptive field, rendering the model more adaptable to size variations within the same class. Moreover, this paper presents a novel anchor-free detector that classifies objects in feature images point-by-point, without relying on anchor boxes. Several experiments on the large remote sensing dataset DIOR challenging Xnet against other popular methods demonstrate that our method attains the best performance, surpassing by 4.7% on the mAP (mean average precision) metric.

Detection of particular meaningful objects in images is of great importance in many fields, including image retrieval or image quality analysis. In this contribution, eleven frequently observed objects (areas) in natural images are learned and detected. The presented algorithm is based on region merging and Bayesian decision theory. The main goal is not perfect recognition, since for that purpose it is necessary to use higher-level knowledge about the image content. Merging of segments proceeds only up to a reliable point, not to merge different categories. Unique merging criteria combine the values of probabilities attached to the segments for all the most likely categories, color and texture features and information about edges. Results are demonstrated on a few images and discussed.

Automatically analyzing morphology of biological objects such as cells, nuclei, and vessels is important for medicine and biology. However, detecting individual biological objects is challenging because biomedical images tend to have a complex structure composed of many morphologically distinct objects and unclear object boundaries. In this paper, we present a novel approach to automatically detect individual objects in biomedical images using a multiple marked point process, in which points are the positions of the objects and marks are their geometric attributes. With this model, we can consider both prior knowledge of the structure of the objects and observed data of an image in object detection. Our proposed method also uses the second generation wavelets-based edge-preserving image smoothing technique to cope with unclear boundaries of biological objects. The experimental results show the effectiveness of our method.

Detecting objects in aerial images is challenging for at least two reasons: (1) target objects like pedestrians are very small in pixels, making them hardly distinguished from surrounding background; and (2) targets are in general sparsely and non-uniformly distributed, making the detection very inefficient. In this paper, we address both issues inspired by observing that these targets are often clustered. In particular, we propose a Clustered Detection (ClusDet) network that unifies object clustering and detection in an end-to-end framework. The key components in ClusDet include a cluster proposal sub-network (CPNet), a scale estimation sub-network (ScaleNet), and a dedicated detection network (DetecNet). Given an input image, CPNet produces object cluster regions and ScaleNet estimates object scales for these regions. Then, each scale-normalized cluster region is fed into DetecNet for object detection. ClusDet has several advantages over previous solutions: (1) it greatly reduces the number of chips for final object detection and hence achieves high running time efficiency, (2) the cluster-based scale estimation is more accurate than previously used single-object based ones, hence effectively improves the detection for small objects, and (3) the final DetecNet is dedicated for clustered regions and implicitly models the prior context information so as to boost detection accuracy. The proposed method is tested on three popular aerial image datasets including VisDrone, UAVDT and DOTA. In all experiments, ClusDet achieves promising performance in comparison with state-of-the-art detectors.

The chapter discusses the design and development of a novel object detection model keeping the motive that anyone and everyone with little to no prior knowledge can easily use it. The object detection is a part of computer vision which deals with detection and localization of objects in images or videos. These systems can be implemented for surveillance, keeping track of goods, robotics, medical field, self-driving cars, and much more. A lot of organizations are using it for various purposes such as it is used by NASA for analysis for deep space analysis, self-driving cars use it for making accurate decisions, and airports use it for security and surveillance. Although it has numerous use cases, but because of complex implementation and need of expertise in the field, it is not being widely used currently. In this chapter, we have made an effort to automate most of the process that a user should do in order to train and use models for object detection. The most complex part of using these technologies is training custom models, and only people having expertise in field are doing it. With the system designed by us, anyone would be able to train custom models on their own and they don’t have to do much for it. Normally, first users have to gather large amount of images and then annotate them 124one by one, which is a tedious and time taking process. One has to do this for thousands of images and each of those images can have multiple instances of various objects to train a model to give a good accuracy. We are automating the whole process with the help of AWS recognition module of AWS. You only look once (YOLO) object detection model is used for automation, as it is fast and accurate at the same time which gives it edge over the other models available for use. This model is based on deep learning to learn through the images provided by user in training phase and then later on can be used to perform detection on images or real-time videos. A graphic user interface (GUI) is also developed, so the users can easily interact with the system and train their own custom models and use as they want it to be used. Data are sent over the AWS servers and retrieve the results using a block of python code, then the response collected from AWS is manipulated and the data are extracted that is required to annotate the images and then processing is done according to the need of our target model. This format can be different for various models which can be used for object detection.

Object detection is a crucial problem in computer vision that involves accurately locating objects in images or videos to identify instances to be detected. It has various applications, including facial detection, intelligent driving assistance, and satellite remote sensing detection. This review aims to aid researchers in quickly comprehending object detection. It covers the concept of object detection algorithms, analyzes the development history of object detection algorithms, and elaborates on the evolution process of object detection algorithms from independent development to combination with deep learning technology. The article divides object detection based on whether anchor boxes are generated during the detection process. It discusses the types of anchor boxes and non-anchor boxes and analyzes the current research status of single-stage and two-stage object detection algorithms. It also summarizes classic model structures in the development process of object detection algorithms and introduces difficulties in object detection. The article aims to solve the problem of object detection with a small number of samples and without detailed annotations during the training process. It summarizes and compares the advantages and disadvantages of various classic models, mainstream datasets, and evaluation indicators. Additionally, it looks forward to current challenges and future development directions in the field of object detection.

Deep learning method of object detection has achieved excellent results, but most of the object detection network training processes are supervised learning. The performance improvement is driven by a large amount of annotation data to drive deeper and more complex network structures. For object detection tasks, it takes 7-42 seconds to complete the precise labeling of a single target rectangle. As the complexity of the scene and the density of objects increase, the cost of labeling becomes higher. In this paper, we propose a semi-supervised object detection framework based on self-training to solve the problem of few training data object detection. We have improved the method of self-training to generate pseudo-labels for object detection tasks, pseudo-labels made by using automatic threshold search and multi-view detection. This method uses semi-supervised learning to mine and utilize unlabeled data, as well as the use of data augmentation methods to enhance the generalization of labeled data. It can achieve high accuracy in object detection models trained with few training data. We proposed several experiments on two publicly available datasets with few training data, and experiments demon-state that our methods based on semi-supervised learning are better than that based on supervised learning.

Object detection from UAV thermal infrared images and videos using YOLO models