Tracking multiple moving objects by binary object forest segmentation

There has been no prior general purpose brain-mind model for multiple events in complex backgrounds. I first discuss that although the age of brain-mind seems to have arrived, the current infrastructure does not well fit the need of research and peer-review for the challenging and important subject of brain-mind. Then, I present a general purpose model of the brain-mind, called the Epigenetic Developer (ED) network model. The model proposes five necessary “chunks” for the brain picture: development, architecture, area, space and time. The development chunk means that any practical brain, natural or artificial, needs to autonomously develop through interactions with the natural environments without any previously given set of tasks. The architecture chunk handles (1) multiple objects in complex backgrounds; (2) reasoning under abstract contexts; (3) multiple sensory modalities and multiple motor modalities and their integration. The area chunk addresses the issue of feature development and area representation, without rigidly specifying what each neuron does. The space chunk deals with spatial attention to individual objects in complex backgrounds, to satisfy the invariance and specificity criteria for type, location, and other concepts. The time chunk indicates that the brain uses its intrinsic spatial mechanisms to deals with time, without dedicated temporal components. The model copes with temporal contexts of events, to satisfy invariance and specificity criteria for time warping, time duration, temporal attention, and long temporal length. The theory and mechanisms are presented and some related experimental results are summarized.

The monitoring of the road freight vehicles traffic on urban roads relies on the work of professionals who need to be fully aware of the traffic on a specific road, and thereby identify the presence of these vehicles in complex scenes. Automatic vehicle identification in video shots may add value to the city life quality, due to congestion diminishment and traffic security improvement. In this research, a model able to identify and segregate road freight vehicles on urban roads is proposed, by means of video analysis and processing, that were recorded by cameras positioned at different angles on highways accesses on urban roads. The system was developed using MATLAB. Techniques related to detecting, targeting and processing steps have been used to identify objects in complex backgrounds. At the end of the work, the system is applied to several scenarios that have been filmed in the city of So Carlos -SP and the results are discussed.

To accurately detect multi-scale remote sensing objects in complex backgrounds, we propose a novel transformer-based adaptive object detection method. The backbone network of the method is a dual attention vision transformer network that utilizes spatial window attention and channel group attention to capture feature interactions between different objects in complex scenes. We further design an adaptive path aggregation network. In the designed network, CBAM (Convolutional Block Attention Module) is utilized to suppress background information in the fusion paths of different-level feature maps, and new paths are introduced to fuse same-scale feature maps to increase the feature information of the feature maps. The designed network can provide more effective feature information and improve the feature representation capability. Experiments conducted on the three datasets of RSOD, NWPU VHR-10, and DIOR show that the mAP of our method is 96.9%, 96.6%, and 81.7%, respectively, which outperforms compared object detection methods. The experimental results show that our method can detect remote-sensing objects better.

An improved YOLOv8s-based method is proposed to address the challenge of accurately recognizing tiny objects in remote sensing images during practical human-computer interaction. In detecting tiny targets, the accuracy of YOLOv8s is low because the downsampling module of the original YOLOv8s algorithm causes the network to lose fine-grained feature information, and the neck network feature information needs to be sufficiently fused. In this method, the strided convolution module in YOLOv8s is replaced with the SPD-Conv module. By doing so, the feature map undergoes downsampling while preserving fine-grained feature information, thereby improving the learning and expressive capabilities of the network and enhancing recognition accuracy. Meanwhile, the path aggregation network is substituted with the SPANet structure, which facilitates the acquisition of more prosperous gradient paths. This substitution enhances the fusion of feature maps at various scales, reduces model parameters, and further improves detection accuracy. Additionally, it enhances the network’s robustness to complex backgrounds. Experimental verification is conducted on the following two intricate datasets containing tiny objects: AI-TOD and TinyPerson. A comparative analysis with the original YOLOv8s algorithm reveals notable enhancements in recognition accuracy. Specifically, under real-time performance constraints, the proposed method yields a 4.9% and 9.1% improvement in mAP0.5 recognition accuracy for AI-TOD and TinyPerson datasets, respectively. Moreover, the recognition accuracy for mAP0.5:0.95 is enhanced by 3.4% and 3.2% for the same datasets, respectively. The results indicate that the proposed method enables rapid and accurate recognition of tiny objects in complex backgrounds. Furthermore, it demonstrates better recognition precision and stability than other algorithms, such as YOLOv5s and YOLOv8s.

Panoramic image object detection has significant applications in autonomous driving, robotic navigation, and security monitoring. However, most current object detection algorithms are trained on pinhole images and cannot be directly applied to panoramic images, which have a large field-of-view (FOV) and distortion. Additionally, research on panoramic image object detection lacks dedicated dataset support, and these images face challenges such as target distortion, occlusion, and multi-scale variations. Existing methods for panoramic image object detection have not yielded satisfactory performance. To address these issues, we propose PanoDetNet, an object detection model based on YOLOv7. We introduce two new modules: the Multi-Scale Feature Fusion (MSFF) module and the Adaptive Panoramic Feature Attention (APFA) module. The MSFF module enhances detection precision for targets of different scales by fusing feature maps of various sizes, while also reducing the number of parameters and simplifying the model structure. The APFA module adaptively addresses the distortion in panoramic images, improving the model’s ability to locate and recognize objects in complex backgrounds and under occlusion. We trained PanoDetNet on our self-built panoramic image object detection dataset, PanoDet. This dataset was collected using a self-developed panoramic camera and manually annotated with the Labelme tool. Experimental results show that PanoDetNet achieves mAP@.5, mAP@.5:.95, and accuracy scores of 95.3%, 75.2%, and 94.1%, respectively. These results represent improvements of 1.6%, 2.5%, and 3.3% over YOLOv7. Our code is available at <uri xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">https://github.com/github98317/PanoDetNet</uri> .

Nowadays, moving object detection in sequence images has become a hot topic in computer vision research, and has a very wide range of practical applications in many fields of military and daily life. In this paper, fast detection of moving objects in complex background is studied, and fast detection methods for moving objects in static and dynamic scenes are proposed respectively. Firstly, based on image preprocessing, aiming at the difficulty of feature extraction of moving targets in low illumination at night, Gamma change is used to process. Secondly, for the fast detection of moving objects in static scenes, this paper designs a detection method combining background difference and edge frame difference. Finally, aiming at the fast detection of moving objects in dynamic scenes, a feature matching detection method based on the SIFT algorithm is designed in this paper. Simulation experiments show that the method designed in this paper has good detection performance.

Efficient waste detection is crucial for environmental sustainability, yet existing models struggle with finegrained objects in complex backgrounds, such as those in the TACO dataset. This paper proposes an attention-centric approach using YOLOv12n to balance detection accuracy and real-time performance. Experimental results on the TACO dataset demonstrate that the proposed YOLOv12n achieves a mean Average Precision (mAP50 ) of 0.376 with an end-to-end inference speed of 94.33 FPS on an NVIDIA RTX 5060 GPU. Ablation studies reveal that removing the Area-Attention ( A2 ) module leads to a significant performance drop, with mAP50 plummeting from 0.376 to 0.148. Furthermore, compared to the YOLOv8n model with a plug-in CBAM module (46.18 FPS, 0.310 mAP), the native attention-centric architecture of YOLOv12n provides a significant increase in inference speed and superior feature localization. This research confirms that a native attention-based design is more effective for realtime fine-grained waste detection than traditional modular additions.

The paper presents a particle filter for integrated detection and tracking of multiple objects in image sequences, using color as the observation feature. The color based feature has been found useful when dealing with non-rigid object deformations, partial occlusions, rapidly changing dynamics and complex backgrounds. The problem of joint detection and tracking is formulated as a hybrid valued sequential state estimation problem, incorporating a discrete variable which represents the number of existing objects. The solution is implemented in the form of a particle filter. The performance of the proposed algorithm is evaluated on various real-world video sequences with objects entering and leaving the scene.

License plate recognition based on SIFT feature

Video image track of basketball flight path can precisely analyze flight trajectory curve in basketball so as to direct basketball shooting training. Thus, this paper puts forward image video sequence analysis and adaptive objective model-based flight trajectory tracking method of basketball. This algorithm fully utilizes correlation of time and space between adjacent blocks. On one hand, in order to overcome effect of basketball rotary motion, matching criterion which is not related to regional location is set up; on the other hand, diamond movement search path is improved based on sport correlation of basketball and center-biased characteristics in order to reduce search times and improve tracking speed. The experiment results show that methods in this paper can effectively track basketball under complex background and have effective robustness of basketball rotary movement and partial occlusion.

This study proposes an Augmented Haar Cascade Classifier (AHCC) to enhance real-time ball detection for humanoid robots operating in dynamic environments. The method integrates Convex Hull mapping, HSV-based segmentation, and Hough Circle validation to overcome challenges such as fluctuating illumination, complex backgrounds, and partial occlusions. Experiments were conducted entirely on a CPU-only Intel NUC platform running ROS without GPU acceleration, using a dataset containing variations in lighting, orientation, scale, and background clutter. Compared with baseline models (standard Haar Cascade Classifier (HCC) and YOLOv5) the proposed AHCC achieved 97% accuracy, 83% recall, 97% precision, and an 89% F1-score, while requiring only 0.00849 s per frame with 8.97% memory usage. Although YOLOv5 reached 99% accuracy, it demanded higher computational resources (0.0344 s per frame, 22.3% memory usage), limiting its practicality for embedded robotic systems. The AHCC therefore offers an optimal balance between detection reliability and computational efficiency, outperforming traditional HCC and providing a lightweight alternative to GPU-dependent detectors such as Tiny-YOLO and MobileNet-SSD.

Detection and analysis of events from video sequences is probably one of the most important research issues in computer vision and pattern analysis society. Before, however, applying methods and tools for analyzing actions, behavior or events, we need to implement robust and reliable tracking algorithms able to automatically monitor the movements of many objects in the scene regardless of the complexity of the background, existence of occlusions and illumination changes. Despite the recent research efforts in the field of object tracking, the main limitation of most of the existing algorithms is that they are not enriched with automatic recovery strategies able to re-initialize tracking whenever its performance severely deteriorates. This is addressed in this paper by proposing an automatic tracking recovery tool which improves the performance of any tracking algorithm whenever the results are not acceptable. For the recovery, non-linear object modeling tools are used which probabilistically label image regions to object classes. The models are also time varying. The first property is implemented in our case using concepts from functional analysis which allow parametrization of any arbitrary non-linear function (with some restrictions on its continuity) as a finite series of known functional components but of unknown coefficients. The second property is addressed by proposing an innovative algorithm that optimally estimates the non-linear model at an upcoming time instance based on the current non-linear models that have been already approximated. The architecture is enhanced by a decision mechanism which permits verification of the time instances in which tracking recovery should take place. Experimental results on a set of different video sequences that present complex visual phenomena (full and partial occlusions, illumination variations, complex background, etc) are depicted to demonstrate the efficiency of the proposed scheme in proving tracking in very difficult visual content conditions. Additionally, criteria are proposed to objectively evaluate the tracking performance and compare it with other strategies.

Vision systems for service robotics applications have to cope with varying environmental conditions, partial occlusions, complex backgrounds and a large number of distractors (clutter) present in the scene. This paper presents a new approach targeted at such application scenarios. It combines segmentation, object recognition, 3D localization and tracking in a seamlessly integrated fashion. We describe our method and give — using a simplified setup — experimental evidence for the viability of the approach.

We propose a fragment based algorithm for efficient target tracking under significant scale variation and partial occlusion. In contrast, none of the previous multiple part or fragment based algorithms are both scale adaptive and robust to partial occlusion. In our algorithm, the target is divided into a number of overlapping image fragments. Their color histograms are compared with those of candidate fragments within the neighborhood in subsequent frames. The candidate fragments with maximum histogram similarity with the template fragments contribute towards selection of location of best match within that neighborhood. Its position is further calibrated by using a localization method. We implement a systematic scale adaptive tracking scheme which is robust to significant changes in the target size. Extensive experimental results based on real life sequences and test datasets are presented which demonstrate the excellent tracking accuracy achieved by our algorithm at real time.

Saliency detection is an active topic in the multimedia field. Most previous works on saliency detection focus on 2D images. However, these methods are not robust against complex scenes which contain multiple objects or complex backgrounds. Recently, depth information supplies a powerful cue for saliency detection. In this paper, we propose a multilayer backpropagation saliency detection algorithm based on depth mining by which we exploit depth cue from three different layers of images. The proposed algorithm shows a good performance and maintains the robustness in complex situations. Experiments' results show that the proposed framework is superior to other existing saliency approaches. Besides, we give two innovative applications by this algorithm, such as scene reconstruction from multiple images and small target object detection in video.