An autonomous target-tracking algorithm based on visual feature is proposed, which combines the Camshift (Continuously Adaptive Mean-Shift) algorithm with the SIFT(Scale-Invariant Feature Transform) one. SIFT algorithm is stable and it is well suited for tracking the object that contains complex color background and more SIFT points. Camshift algorithm is suited for the case of simplex color. In this paper, the advantages of the two algorithms are fused to implement a real-time system for autonomous moving object detecting and target tracking, which shows good performance in the case with any color distribution. Compared to the traditional separated Camshift and SIFT algorithm, the proposed algorithm is validated by the experiments.
New daily persistent headache (NDPH) is a rare primary headache disorder characterized by daily and persistent sudden onset headaches. Specific abnormalities in gray matter and white matter structure are associated with pain, but have not been well studied in NDPH. The objective of this work is to explore the fiber tracts and structural connectivity, which can help reveal unique gray and white matter structural abnormalities in NDPH. The regional radiomics similarity networks were calculated from T1 weighted (T1w) MRI to depict the gray matter structure. The fiber connectivity matrices weighted by diffusion metrics like fractional anisotropy (FA), mean diffusivity (MD) and radial diffusivity (RD) were built, meanwhile the fiber tracts were segmented by anatomically-guided superficial fiber segmentation (Anat-SFSeg) method to explore the white matter structure from diffusion MRI. The considerable different neuroimaging features between NDPH and healthy controls (HC) were extracted from the connectivity and tract-based analyses. Finally, decision tree regression was used to predict the clinical scores (i.e. pain intensity) from the above neuroimaging features. T1w and diffusion MRI data were available in 51 participants after quality control: 22 patients with NDPH and 29 HCs. Significantly decreased morphological similarity was found between the right superior frontal gyrus and right hippocampus. The superficial white matter (SWM) showed significantly decreased FA in fiber tracts including the right superficial-frontal, left superficial-occipital, bilateral superficial-occipital-temporal (Sup-OT) and right superficial-temporal, meanwhile significant increased RD was found in the left Sup-OT. For the fiber connectivity, NDPH showed significantly decreased FA in the bilateral basal ganglion and temporal lobe, increased MD in the right frontal lobe, and increased RD in the right frontal lobe and left temporal-occipital lobe. Clinical scores could be predicted dominantly by the above significantly different neuroimaging features through decision tree regression. Our research indicates the structural abnormalities of SWM and the neural pathways projected between regions like right hippocampus and left caudate nucleus, along with morphological similarity changes between the right superior frontal gyrus and right hippocampus, constitute the pathological features of NDPH. The decision tree regression demonstrates correlations between these structural changes and clinical scores.
As a relatively successful recommendation system, the collaborative filtering recommendation system (CFRS) has been widely used in e-commerce. However, the current CFRS is mainly based on mainstream or popular products to recommending similar items for users and is less efficiency in recommend the so called "Long Tail" products to meet the individual needs of users. Based on the Item-based system filtering recommendation algorithm, this paper proposes a collaborative filtering recommendation algorithm that implements long tail recommendation by using the item rating probability matrix and item rating reliability. Compared with the traditional collaborative filtering algorithm, the experimental result based on MovieLens 1M dataset shows that the proposed algorithm can deal with the data sparsity problem better, and is better for producing recommendation for the long tail products effect, and furthermore, it shows stability to a certain extent in producing recommendations under different situations of data sparseness.
In this paper, we proposed a dual-band underwater image denoising and enhancement algorithm, first the original image was decomposed into high-frequency part H and lowfrequency part L, and then H was filtered into F by mean shift algorithm which was improved by using the intermediate iteration results.A contrast enhancement method was proposed based on the haze imaging model and was applied on L and F. experiment results demonstrate the effectiveness of the proposed algorithm.
Crowd counting is a challenging task due to the issues such as scale variation and perspective variation in real crowd scenes. In this paper, we propose a novel Cascaded Residual Density Network (CRDNet) in a coarse-to-fine approach to generate the high-quality density map for crowd counting more accurately. (1) We estimate the residual density maps by multi-scale pyramidal features through cascaded residual density modules. It can improve the quality of density map layer by layer effectively. (2) A novel additional local count loss is presented to refine the accuracy of crowd counting, which reduces the errors of pixel-wise Euclidean loss by restricting the number of people in the local crowd areas. Experiments on two public benchmark datasets show that the proposed method achieves effective improvement compared with the state-of-the-art methods.
Aiming at the difficulty of missing, wrong and reverse detection in PCB component detection, the paper proposes a new PCB defect detection and elimination based on visual recognition technology and computer-aided system, it can find out target more efficiently by visual inspection technology in the non-stop line. The target region was marked through secondary error matching algorithm, the threshold segmentation graph of original images were investigated in the marked region. The recognition capability for missing and wrong detection was enhanced. The component matching compatibility was analyzed by mask operation and statistical histogram algorithm. The recognition capability for polarity detection was enhanced. The results were judged by computer aided evaluation system that was carried out under the environment of Vision Pro and Visual Studio. The dynamic position of defective component was calculated by PLC. The operation results showed that through the proposed method, the recognition rate was 100%, and the false alarm rate was about 3% in the detection of anti logic, color components, pins and capacitance, and meet the needs of real-time detection and elimination.
In order to make segmentation more robust and accurate in the underwater environment, a two-stage segmentation method is proposed in this paper. In preprocessing stage, a dual-band enhancing technique is used to preserve the target contour and at the same time eliminate the fake edges generated by the noises; in segmentation stage, edge-grouping method is chosen for its advantageous characteristics over noisy images. Experimental results show that the proposed method can get a better performance both in stability and accuracy.
Computer Vision has attracted more and more attention with the fast development of deep learning. The instance segmentation area, which extends the Object detection, can better help us comprehend the surrounding environments. In this paper, we ensembled the tricks that can strengthen the model performance for instance segmentation. We do the ablation experiments for the MS-COCO datasets and LVIS datasets. The results demonstrate that the selected tricks can greatly boost the performance. With our tricks, our model achieves the 7th on the LVIS Challenge Track for ICCV 2019 workshop.
Incremental learning or online learning as a branch of machine learning has attracted more attention recently. For large-scale problems and dynamic data problem, incremental learning overwhelms batch learning, because of its efficient treatment for new data. However, class imbalance problem, which always appears in online classification brings a considerable challenge for incremental learning. The serious class imbalance problem may directly lead to a useless learning system. Cost-sensitive learning is an important learning paradigm for class imbalance problems and widely used in many applications. In this article, we propose an incremental cost-sensitive learning method to tackle the class imbalance problems in the online situation. This proposed algorithm is based on a novel cost-sensitive support vector machine, which uses the Linear-exponential (LINEX) loss to implement high cost for minority class and low cost for majority class. Using the half-quadratic optimization, we first put forward the algorithm for the cost-sensitive support vector machine, called CSLINEX-SVM*. Then we propose the incremental cost-sensitive algorithm, ICSL-SVM. The results of numeric experiments demonstrate that the proposed incremental algorithm outperforms some conventional batch algorithms except the proposed CSLINEX-SVM*.
With the increasing number of vehicles, vehicle detection has become an important part of intelligent transportation system. At present, most detection algorithms are only suitable for normal light conditions, but the detection performance is poor for low illumination conditions. In order to achieve effective vehicle detection under low illumination conditions, this paper proposes an image enhancement algorithm to increase the contrast of the image, thereby greatly improving the effect of vehicle detection. First, the image contrast is enhanced through an adaptive contrast stretching algorithm. Secondly, the bilateral filtering algorithm is used to filter out the noise in the image. Finally, the detection system based on Haar features and AdaBoost classifier is used to detect vehicles. Experimental results show that the proposed algorithm can effectively enhance image contrast, highlight vehicle information, and the vehicle detection accuracy rate under low illumination conditions reaches 87.04%.
'/%3e%3cuse xlink:href='%23a' transform='rotate(23.036 .093 25.536)'/%3e%3cuse xlink:href='%23a' transform='rotate(45.87 1.273 16.18)'/%3e%3cuse xlink:href='%23a' transform='rotate(69.945 .996 12.078)'/%3e%3cuse xlink:href='%23a' transform='rotate(20.66 -19.689 31.932)'/%3e%3c/svg%3e)
