Apple object detection based on improved YOLOX

Multi-scale object detection in natural scenes is still challenging. To enhance the multi-scale perception capability, some algorithms combine the lower-level and higher-level information via multi-scale feature fusion strategies. However, the inherent spatial properties among instances and relations between foreground and background are ignored. In addition, the human-defined “center-based” regression quality evaluation strategy, predicting a high-to-low score based on a linear relationship with the distance to the center of ground-truth box, is not robust to scale-variant objects. In this work, we propose a Depth-Guided Progressive Network (DGPNet) for multi-scale object detection. Specifically, besides the prediction of classification and localization, the depth is estimated and used to guide the image features in a weighted manner to obtain a better spatial representation. Therefore, depth estimation and 2D object detection are simultaneously learned via a unified network, where the depth features are merged as auxiliary information into the detection branch to enhance the discrimination among multi-scale objects. Moreover, to overcome the difficulty of empirically fitting the localization quality function, high-quality predicted boxes on scale-variant objects are more adaptively obtained by an IoU-aware progressive sampling strategy. We divide the sampling process into two stages, i.e., “statistical-aware” and “IoU-aware”. The former selects thresholds for positive samples based on statistical characteristics of multi-scale instances, and the latter further selects high-quality samples by IoU on the basis of the former. Therefore, the final ranking scores better reflect the quality of localization. Experiments verify that our method outperforms state-of-the-art methods on the KINS and Cityscapes dataset.

In this paper, we consider water surface object detection in natural scenes. Generally, background subtraction and image segmentation are the classical object detection methods. The former is highly susceptible to variable scenes, so its accuracy will be greatly reduced when detecting water surface objects due to the changing of the sunlight and waves. The latter is more sensitive to the selection of object features, which will lead to poor generalization as a result, so it cannot be applied widely. Consequently, methods based on deep learning have recently been proposed. The River Chief System has been implemented in China recently, and one of the important requirements is to detect and deal with the water surface floats in a timely fashion. In response to this case, we propose a real-time water surface object detection method in this paper which is based on the Faster R-CNN. The proposed network model includes two modules and integrates low-level features with high-level features to improve detection accuracy. Moreover, we propose to set the different scales and aspect ratios of anchors by analyzing the distribution of object scales in our dataset, so our method has good robustness and high detection accuracy for multi-scale objects in complex natural scenes. We utilized the proposed method to detect the floats on the water surface via a three-day video surveillance stream of the North Canal in Beijing, and validated its performance. The experiments show that the mean average precision (MAP) of the proposed method was 83.7%, and the detection speed was 13 frames per second. Therefore, our method can be applied in complex natural scenes and mostly meets the requirements of accuracy and speed of water surface object detection online.

Recent research on neocognitron-like neural feed-forward architectures, which have formerly been successfully applied to the recognition of artificial stimuli such as paperclip objects, now also opens up application to more natural stimuli. Such networks exhibit high-recognition performance with respect to translation, rotation, scaling and cluttered surroundings. In this contribution, we introduce a new type of hierarchical model, which is trained using a non-negative matrix factorization algorithm. In contrast to previous work, our approach cannot only classify objects but is also capable of rapid object detection in natural scenes. Thus, the time-consuming and conceptually unsatisfying split-up into a localization stage (e.g., using segmentation) and a subsequent classification can be avoided. The network consists of alternating layers of simple and complex cell planes and incorporates nonlinear processing schemes that have been proposed in recent literature. Learning of receptive field profiles for the lower layers of the network takes place by unsupervised learning whereas a final classification layer is trained supervised. This final layer is then utilized for detection. We test the classification performance of the network on images of natural objects which are systematically distorted. To test the ability to detect objects, cluttered natural background is used.

We propose a novel edge detection method based on fractal coding. We point out that the mean-square-error distance (MSED) of fractal coding can be used to extract edges of a fractal image effectively. The algorithm for edge detection based on fractal coding MSED is given and its improvement is discussed. Results indicate that since the new algorithm for edge detection avoids the gradient operation, it is insensitive to noise and suitable for object detection in natural scenes based on edges.

Person detection is an important prerequisite of social interaction, but is not well understood. Following suggestions that people in the visual field can capture a viewer's attention, this study examines the role of the face and the body for person detection in natural scenes. We observed that viewers tend first to look at the center of a scene, and only then to fixate on a person. When a person's face was rendered invisible in scenes, bodies were detected as quickly as faces without bodies, indicating that both are equally useful for person detection. Detection was optimized when face and body could be seen, but observers preferentially fixated faces, reinforcing the notion of a prominent role for the face in social perception. These findings have implications for claims of attention capture by faces in that they demonstrate a mediating influence of body cues and general scanning principles in natural scenes.

Text detection in natural scenes is fundamental for text image analysis. In this paper, we propose a context-based approach for robust and fast text detection. Our main contribution is that we introduce a new concept of key region, which is described with context according to stroke properties, appearance consistency and specific spatial distribution of text line. With such context descriptors, we adopt SVM to learn a context-based classifier to find key regions in candidate regions. Therein, candidate regions are connected components generated by local binarization algorithm in the areas, which are detected by an offline learned text patch detector. Experimental results on two benchmark datasets demonstrate that our approach has achieved competitive performances compared with the state-of-the-art algorithms including the stroke width transform (SWT) [1] and the hybrid approach based on CRFs [2] with speedup rates of about 1.7x~4.4x.

The object contour detection in natural scenes is an important research problem in computer vision. The difficulty is that the integrity of contour extracted is interfered with a large number of texture edges in the background seriously. In recent years, some researchers have introduced image contour detection method with biological visual features and achieved preferable results. Such as, based on the fact of visual outer region suppression, they can suppress a certain amount of texture edge while extracting the contour of the object, and obtain the proper contour edge. However, when this method is used for contour detection in some image which the texture is similar to the contour, the texture edge still cannot be removed well, and the result is unsatisfactory. In consideration of the merit and demerit of the feature suppressed method, we propose an improved algorithm for object contour detection in natural scene based on image saliency. Firstly, the initial contour is obtained by using the suppression effect of non-classical receptive field, and the saliency map is obtained by using the hyper-complex Fourier transform image saliency detection method, and then the initial contour and the saliency map are integrated into the final contour. Compared with the traditional contour detection method, the contour extraction algorithm based on image saliency can remove more background information and improve the accuracy and integrity of object contour extracted in natural scenes.

As an important core in the intelligent traffic management system, the technology and application of license plate recognition have become research focus. Detecting the accurate location of a license plate from a vehicle image is considered to be the most crucial step of license plate recognition, which greatly affects the recognition rate and speed of the whole system. Nevertheless, due to the low accuracy of license plate detection in natural scenes, further investigations are still needed in this field in order to make the detection process very efficient. In this paper, We have studied and implemented a convolutional neural network license plate detection algorithm based on transfer learning. According to the invention, new energy license plates and ordinary license plates are adopted as the research objects. The text detection model AdvancedEAST is trained on the license plate images through the transfer learning method, and experiments are carried out on the self-built license plate dataset. The experimental results show that the algorithm can better adapt to light complexity, low resolution, target interference, license plate tilt and other complex conditions. The license plate positioning algorithm has high accuracy in natural scenes, and it is superior to the traditional license plate detection methods.

Previous approaches for scene text detection have already achieved promising performances across various benchmarks. However, they usually fall short when dealing with challenging scenarios, even when equipped with deep neural network models, because the overall performance is determined by the interplay of multiple stages and components in the pipelines. In this work, we propose a simple yet powerful pipeline that yields fast and accurate text detection in natural scenes. The pipeline directly predicts words or text lines of arbitrary orientations and quadrilateral shapes in full images, eliminating unnecessary intermediate steps (e.g., candidate aggregation and word partitioning), with a single neural network. The simplicity of our pipeline allows concentrating efforts on designing loss functions and neural network architecture. Experiments on standard datasets including ICDAR 2015, COCO-Text and MSRA-TD500 demonstrate that the proposed algorithm significantly outperforms state-of-the-art methods in terms of both accuracy and efficiency. On the ICDAR 2015 dataset, the proposed algorithm achieves an F-score of 0.7820 at 13.2fps at 720p resolution.

With the worldwide spread of COVID-19, people's life safety has been greatly threatened. So, we consider using YOLOv3-tiny algorithm to detect mask wearing. Since there are few detection models for correctly wearing masks, we decided to use three classifications to detect correctly wearing masks, incorrectly wearing masks, and not wearing masks. Besides, in order to enhance the performance of our model in small object detection, we propose the k-means++ algorithm to make the size of the initial anchor boxes closer to the actual size of the object, and add a YOLO detection layer to effectively improve the accuracy of a small object. The results show that the mAP@50 values of our model are 4.68% higher than YOLOv3-tiny algorithm. Our model has significantly improved the detection ability of crowd scenes, and mask detection is more accurate and robust, which has good application value for mask detection in natural scenes.

Reliable detection of fiducial targets in real-world images is addressed in this paper. We show that even the best existing schemes are fragile when exposed to other than laboratory imaging conditions, and introduce an approach which delivers significant improvements in reliability at moderate computational cost. The key to these improvements is in the use of machine learning techniques, which have recently shown impressive results for the general object detection problem, for example in face detection. Although fiducial detection is an apparently simple special case, this paper shows why robustness to lighting, scale and foreshortening can be addressed within the machine learning framework with greater reliability than previous, more ad-hoc, fiducial detection schemes.

The non-maximum suppression (NMS) algorithm, which merges neighboring bounding boxes as the detection result, is widely utilized in object detection methods. However, the traditional NMS algorithm is not suitable for text detection in natural scenes, especially for long texts and dense texts. In this paper, we observe that the coordinates of candidate bounding boxes are presented in skew distribution. On this observation, an improved NMS algorithm called SD-NMS (Skew Distribution NMS) is designed. First, the mode and the median of the coordinate set are counted to filter out the redundant bounding boxes. Then the left bounding boxes are merged for the location of the text regions. The SD-NMS method improves the detection ability of the model without extra model training and can be easily embedded in text detection methods. The experimental results show that our method obtains F-measure more than other NMS methods in public data sets ICDAR2015 and MSRATD500.

Text in images provides rich and accurate high-level semantic information, which is of great significance for many potential applications such as scene understanding, image and video retrieval. As a necessary means of understanding scene text, text detection has been widely concerned in the field of computer vision in recent years. However, due to the diversity of text scale and the uncertainty of image quality, text detection in natural scenes is still a challenging problem. Inspired by the successful application of deep neural network in target detection task, this paper proposes a text detection method based on multi-level feature extraction combined with deep learning technology. The multi-level feature extraction designed by this method can capture the details of the text, which is conducive to enhance the robustness of the algorithm to small-scale text and low-resolution images. In addition, the method is end-to-end, and can output text detection results directly. This paper evaluates the method on several standard datasets, and the experimental results prove the effectiveness of the proposed method.

A systematic comparison between visual cues for boundary detection

Text detection in natural scenes is a current research hotspot. The Efficient and Accurate Scene Text (EAST) detector model has fast detection speed and good performance but is ineffective in detecting long text regions owing to its small receptive field. In this study, we built upon the EAST model by improving the bounding box’s shrinking algorithm to make the model more accurate in predicting short edges of text regions; altering the loss function from balanced cross-entropy to Focal loss; improving the model’s learning ability on hard, positive examples; and adding a feature enhancement module (FEM) to increase the receptive field of the EAST model and enhance its detection ability for long text regions. The improved EAST model achieved better detection results on both the ICDAR2015 dataset and the Street Sign Text Detection (SSTD) dataset proposed in this paper. The precision and F1 scores of the model also demonstrated advantages over other models on the ICDAR2015 dataset. A comparison of the text detection effects between the improved EAST model and the EAST model showed that the proposed FEM was more effective in increasing the EAST detector’s receptive field, which indicates that it can improve the detection of long text regions.