A 5-chunk developmental brain-mind network model for multiple events in complex backgrounds

Tracking multiple moving objects by binary object forest segmentation

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.

Females of many species choose mates using multiple sensory modalities. Multimodal noise may arise, however, in dense aggregations of animals communicating via multiple sensory modalities. Some evidence suggests multimodal signals may not always improve receiver decision-making performance. When sensory systems process input from multimodal signal sources, multimodal noise may arise and potentially complicate decision-making due to the demands on cognitive integration tasks. We tested female túngara frog, Physalaemus (=Engystomops) pustulosus, responses to male mating signals in noise from multiple sensory modalities (acoustic and visual). Noise treatments were partitioned into three categories: acoustic, visual, and multimodal. We used natural calls from conspecifics and heterospecifics for acoustic noise. Robotic frogs were employed as either visual signal components (synchronous vocal sac inflation with call) or visual noise (asynchronous vocal sac inflation with call). Females expressed a preference for the typically more attractive call in the presence of unimodal noise. However, during multimodal signal and noise treatments (robofrogs employed with background noise), females failed to express a preference for the typically attractive call in the presence of conspecific chorus noise. We found that social context and temporal synchrony of multimodal signaling components are important for multimodal communication. Our results demonstrate that multimodal signals have the potential to increase the complexity of the sensory scene and reduce the efficacy of female decision making.

The central role of the temporo-parietal junction and the superior longitudinal fasciculus in supporting multi-item competition: Evidence from lesion-symptom mapping of extinction

X-ray imaging allows for the visualization of the internal structure of an object. However, the capture of motion trajectories of weakly absorbing objects in complex backgrounds remains challenging due to low contrast and structural overlap. To address this issue, move contrast X-ray imaging (MCXI) is employed to enhance dynamic features without the use of contrast agents and to provide strong robustness against noise. A fringe-based background model was constructed to simulate and analyze variations in motion trajectories under various influencing factors, including relative contrast, motion speed, background fluctuation frequency, and noise level. Quantitative metrics-such as trajectory intensity, integrity, and signal-to-noise ratio-were used to evaluate the performance of the proposed method. MCXI enables the identification of motion paths and spatial velocity distributions of weakly absorbing objects, even under high-noise conditions, demonstrating high robustness and sensitivity. The effectiveness, sensitivity, and noise resistance of the method were validated through experiments involving oil-water motion. In addition, the integration of the CUDA acceleration algorithm significantly improves the efficiency of processing high-throughput dynamic data.

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.

Building extraction is significant in urban planning, economic evaluation, and driverless technology development. However, automatic building extraction from high spatial resolution remote sensing images has been a challenging task due to the various building shapes and colors, imaging conditions, and complex background objects. Current methods in building extraction are generally based on deep convolution networks, and they mostly use an encoder-decoder architecture, wherein detailed building features and small buildings are easily omitted in continuous convolution operations. Moreover, buildings with blurred boundaries are only completely extracted with difficulty. To meet these challenges, we propose a multi-task architecture of frequency-spatial learning Transformer to extract buildings from high spatial resolution remote sensing images. Different from current architecture, we designed a frequency-spatial learning module in the framework of multi-task to synthesize the multi-scale spatial features and frequency decomposition features of high-resolution image. Spiking convolution is proposed in this study to enhance the frequency features of buildings by mimicking the neural transmission in human brains. In this way, multi-scale building features can be better preserved and distinguished from background objects. Moreover, a masked-attention Transformer is adopted to improve multi-scale building mask prediction accuracy by synthesizing successive pixel-wise up-sampled feature maps. We also propose a strategy to evaluate the practical transferability of the proposed method by mimicking practical application cases through training and evaluating images with different spatial resolutions from different study areas and datasets. Experiments using five public building datasets (WHU-Building Satellite Dataset I, WHU-Building Satellite Dataset II, Massachusetts Buildings Dataset, Inria Aerial Image Dataset, xBD Building Dataset) demonstrate the strong potential applicability of our proposed method for practical application cases. Our method outperforms five recently proposed state-of-the-art semantic segmentation methods with 36.60% accuracy improvement on extracted buildings and approximately 53.55% recall progress in extracting small building instances. The implementation code will be released after the paper is published.

The paper proposes a novel method for human face extraction from color images, characterized by uncontrolled illumination conditions and complex backgrounds. The method incorporates stationary Haar wavelet transform & proximity influence for prominent boundaries detection and watershed transform, proximity influence & morphological operations to separate foreground / background along with region and color attributes for human face extraction. The method exploits redundancy by coalescing local color cues of all color channels to emphasize reliable processing to precisely detect the human face by avoiding under-segmentation and reducing over-segmentation & artifacts. The method has been tested on face-image collection of standard database and on images captured by an amateur photographer for various complex backgrounds having diversified textures, varied illumination conditions and multiple background objects. The presented results show the effectiveness of the method for human face extraction, proving it suitable as an input to applications like digital album catalogue, content based image retrieval, face recognition and facial expression recognition.

Manatees are herbivorous aquatic mammals found in the coastal and inland waters of the Atlantic Ocean. All three manatee species are currently listed as vulnerable on the IUCN red list and there still remains much unknown about their ecology. It is currently unknown what sensory modalities manatees use to locate their food in the wild. A literature review of the Paenungulata clade (sirenians, proboscideans, and hyracoideans) was conducted in order to compare and contrast what is known about the sensory modalities of the clade, to better understand the sensory modalities of manatees, particularly the ones they use to locate their food. Manatees have a higher frequency range for hearing than elephants, who have the best low-frequency hearing range known to mammals; hearing range of hyrax is unknown. All members of Paenungulata have vibrissae assisting in tactile abilities and potentially compensate for other senses such as hearing or vision. The ability to smell in manatees and hyrax is unknown, but elephants have been found to have an excellent sense of smell. Manatees, elephants, and hyrax have dichromatic vision. A preliminary experiment was designed to test manatee feeding modalities in the wild. The objectives of this study were to determine if the proposed methodology, modified for an aquatic environment from Renda &amp; Roux (2017), was capable of testing manatee sensory use by limiting the sensory cues provided. Sensory modalities used in locating food were tested in two ways: when they know where the food is located, within a short distance, and when the food is placed randomly throughout their habitat, at long distances. In this study, we were able to show that the experimental design works, and provide preliminary data. In the short distance dichotomous choice trials, the percent of correct choices were 67% for the chemoreception + vision, 60% for chemoreception only, and 60% for vision only, with 50% being the rate of chance. For long distance experiments, the mean minimum time in hours it took manatees to consume the food placed randomly along their habitat of San San-Pond Sak River, Panama was 12.0 hours for chemoreception + vision, more than 22 hours for chemoreception only, and 6.89 hours for the control (no box). Due to the small sample size, no definitive conclusion could be made as to which sensory modality manatees use to find food, but our results support the idea that manatees use multiple modalities, chemoreception + vision, to locate food. Additional trials are needed in order to perform statistical analysis on the data.

Automated ripeness detection in large-scale strawberry cultivation is often challenged by complex backgrounds, significant target scale variation, and small object size. To address these problems, an efficient strawberry ripeness detection model, YOLOv11-HRS, is proposed. This model incorporates a hybrid channel–space attention mechanism to enhance its attention to key features and to reduce interference from complex backgrounds. Furthermore, the RepNCSPELAN4_L module is devised to enhance multi-scale target representation through contextual feature aggregation. Simultaneously, a 160 × 160 small-target detection head is embedded in the feature pyramid to enhance the detection capability of small targets. It replaces the original SPPF module with the higher-performance SPPELAN module to further enhance detection accuracy. Experimental results on the self-constructed strawberry dataset SRD show that YOLOv11-HRS improves mAP@0.5 and mAP@0.5:0.95 by 3.4% and 6.3%, respectively, reduces the number of parameters by 19%, and maintains a stable inference speed compared to the baseline YOLOv11 model. This study presents an efficient and practical solution for strawberry ripeness detection in natural environments. It also provides essential technical support for advancing intelligent management in large-scale strawberry cultivation.