Object Counting Research Articles

Detection and Localization of Early-Stage Multiple Brain Tumors Using a Hybrid Technique of Patch-Based Processing, k-means Clustering and Object Counting.

Brain tumors are a major health problem that affect the lives of many people. These tumors are classified as benign or cancerous. The latter can be fatal if not properly diagnosed and treated. Therefore, the diagnosis of brain tumors at the early stages of their development can significantly improve the chances of patient's full recovery after treatment. In addition to laboratory analyses, clinicians and surgeons extract information from medical images, recorded by various systems such as magnetic resonance imaging (MRI), X-ray, and computed tomography (CT). The extracted information is used to identify the essential characteristics of brain tumors (location, size, and type) in order to achieve an accurate diagnosis to determine the most appropriate treatment protocol. In this paper, we present an automated machine vision technique for the detection and localization of brain tumors in MRI images at their very early stages using a combination of k-means clustering, patch-based image processing, object counting, and tumor evaluation. The technique was tested on twenty real MRI images and was found to be capable of detecting multiple tumors in MRI images regardless of their intensity level variations, size, and location including those with very small sizes. In addition to its use for diagnosis, the technique can be integrated into automated treatment instruments and robotic surgery systems.

Supervised approach for object identification using speeded up robust features

This paper proposes a vision based novel approach for real-time object counting. The proposed approach uses the textural information for object counting. Speeded up robust features (SURF) are used to extract the textural information from the image. Firstly, the approach selects stable SURF features from prototype image, i.e., object of interest. These features are matched with the SURF features of scene image captured using vision interface. Feature grid vectors (FGVs) and feature grid clusters (FGCs) are formed for matched SURF features in the scene to indicate the presence of object. Support vector machine (SVM) learning is used to identify true instances of the object. A parameter tuning approach is used to find optimised heuristics for more accuracy and less computation. The proposed approach performs well irrespective of illumination, rotation and scale. A run time environment of the proposed approach is also developed to get real-time status of the object count.

Fast-D: When Non-Smoothing Color Feature Meets Moving Object Detection in Real-Time

The moving object detection refers to the detection of physical moving objects from a video, which is applied in video surveillance, object recognition, object counting, human-computer interaction, and so on. Moreover, nowadays, real-time moving object detection is used as services in the cloud, edge, and fog computing. However, the existing methods do not meet the trade-off between accuracy and complexity. To address these issues, we present a background subtraction-based moving object detection method, called Fast-D. In this paper, we look at the ‘non-smoothing color feature’ to make the moving object detection more robust in real-time. Each color feature is given equal significance during the classification of a pixel. Background model and threshold are initialized for each pixel. And then, the background model and threshold are updated dynamically when there are changes in the background of the video. Adaptive post-processing is considered to discard salt and pepper noise and fill holes in the detected moving object silhouettes. The evaluation of our proposed method on four complex datasets exhibits the significance.

Supervised approach for object identification using speeded up robust features

This paper proposes a vision based novel approach for real-time object counting. The proposed approach uses the textural information for object counting. Speeded up robust features (SURF) are used ...

Deep Learning-based Object Recognition for Counting Car Components to Support Handling and Packing Processes in Automotive Supply Chains

Abstract Complex distributed supply chains, e.g., in the automotive industry, need to cope with high product variety. Digital image processing can use specific geometric and optical properties of parts and components for determining their type and thus needs no external markers. It is thus well applicable to supply chain processes that involve direct handling of many different product components and need no individual identification of items. An example of such a process is counting items of different product types during packing. In this paper, we use deep learning-based digital image processing methods in order to distinguish and count the number of objects of two different types of automotive components in standardized transport bins, detected by time-of-flight (ToF) depth sensors. Classical watershed object counting methods are adapted to depth data and support the fast generation of training data for the deep learning-based classification methods. The proposed method is applied to an automotive supply chain, and it is demonstrated that car components can be counted with good reliability during packing into transport bins. Thus, digital image processing can be useful to supplement auto-identification and sensor technologies and complete digital end-to-end monitoring of supply chains.

Density and Time based Traffic Control System using Video Processing

Traffic is the serious issue which each nation faces due to the expansion in number of vehicles. One of the strategies to beat the traffic issue is to build up a smart traffic control framework which depends on computing the traffic density and about utilizing constant video and picture preparing procedures. The topic is to control the traffic by deciding the traffic density on each roadside and control the traffic signal smartly by utilizing the density data. In this paper, an automated system based on processing of real time videos is proposed for detection of vehicles and recording count of them. The System will consist of various stages which includes Object Car Detection and Signal variation based on density. Captured video will be converted into frames and which will be pre-processed for object detection using Haar-Cascade than detected object count will be used to obtain the density and manipulate the signal accordingly. The density count algorithm works by contrasting the ongoing edge of live video by the reference picture and via looking through vehicles just in the district of intrigue (for example street region). The figured vehicle thickness can be contrasted and other course of the traffic so as to perform control of the traffic flags in more smart and proficient manner.

TasselNetv2: in-field counting of wheat spikes with context-augmented local regression networks

BackgroundGrain yield of wheat is greatly associated with the population of wheat spikes, i.e., spike~number~text {m}^{-2}. To obtain this index in a reliable and efficient way, it is necessary to count wheat spikes accurately and automatically. Currently computer vision technologies have shown great potential to automate this task effectively in a low-end manner. In particular, counting wheat spikes is a typical visual counting problem, which is substantially studied under the name of object counting in Computer Vision. TasselNet, which represents one of the state-of-the-art counting approaches, is a convolutional neural network-based local regression model, and currently benchmarks the best record on counting maize tassels. However, when applying TasselNet to wheat spikes, it cannot predict accurate counts when spikes partially present.ResultsIn this paper, we make an important observation that the counting performance of local regression networks can be significantly improved via adding visual context to the local patches. Meanwhile, such context can be treated as part of the receptive field without increasing the model capacity. We thus propose a simple yet effective contextual extension of TasselNet—TasselNetv2. If implementing TasselNetv2 in a fully convolutional form, both training and inference can be greatly sped up by reducing redundant computations. In particular, we collected and labeled a large-scale wheat spikes counting (WSC) dataset, with 1764 high-resolution images and 675,322 manually-annotated instances. Extensive experiments show that, TasselNetv2 not only achieves state-of-the-art performance on the WSC dataset (91.01% counting accuracy) but also is more than an order of magnitude faster than TasselNet (13.82 fps on 912times 1216 images). The generality of TasselNetv2 is further demonstrated by advancing the state of the art on both the Maize Tassels Counting and ShanghaiTech Crowd Counting datasets.ConclusionsThis paper describes TasselNetv2 for counting wheat spikes, which simultaneously addresses two important use cases in plant counting: improving the counting accuracy without increasing model capacity, and improving efficiency without sacrificing accuracy. It is promising to be deployed in a real-time system with high-throughput demand. In particular, TasselNetv2 can achieve sufficiently accurate results when training from scratch with small networks, and adopting larger pre-trained networks can further boost accuracy. In practice, one can trade off the performance and efficiency according to certain application scenarios. Code and models are made available at: https://tinyurl.com/TasselNetv2.

Novel Platform for Droplet Detection and Size Measurement Using Microstrip Transmission Lines.

We propose a novel platform for detecting as well as measuring the size of individual droplets in microfluidic channels using microstrip transmission lines. The most outstanding feature of our platform is that, as opposed to previous related works, its design allows for the droplet to flow in a microfluidic channel fabricated between the top strip and the ground plane of a microstrip transmission line. This provides enhanced interaction of the electromagnetic field with the detected droplets. The proposed design allows us to measure droplet size directly from the phase of the microwave signal, without the need for a resonator. The platform is based on low temperature co-fired ceramic (LTCC), which makes it more compatible with Radiofrequency (RF) and microwave technology than platforms used in previous works. With this platform, we are able to measure droplets as small as 150 µm in radius. It is worth pointing out that our device could also be used for detection, counting and measurement of other microscopic objects.

Drug-seeking: A literature review (and an exemplar of stigmatization in nursing).

Despite its lack of conceptual clarity and uniform definition, the term drug-seeking is used frequently by nurses from a variety of practice environments. The drugs patients are referred to as seeking are often pain medications. This is important because nursing has widely adopted a patient-centric definition of pain. Nursing also has a robust ethical code that places high value on human dignity and nurses' role in patient advocacy. A review of literature was conducted with the aims of describing whether/how the term drug-seeking has changed over time and to determine whether the use of the term in nursing literature is consistent with nursing values. Use of the term has shifted from objective counts of patient requests for medication to a confusing mixture of observable patient behavior and subjective interpretations of patient motivation. Its use is not consistent with nursing values. It is, in fact, a good illustration of stigmatization in nursing. Stigmatization is contrary to nursing values. Nurses in practice, research, education, authors, reviewers, and editors all have a role in ending this stigmatization.

Bilateral counting network for single-image object counting

This paper proposes a novel bilateral counting network to estimate the accurate and robust counting result for single-image object counting task. The proposed network is composed of two main components: the concentrated dilated pyramid module and dual-context extraction path. The concentrated dilated pyramid module extracts the multi-scale feature from the image to address the scale variant issue in object counting task via a pyramid structure and also uses a shortcut concentration to facilitate the back-propagation of the gradient so as to improve the counting performance. And the dual-context extraction path obtains different-level context related to the object counting task through convoluting and down-sampling the image different times. The concentrated dilated pyramid module and the dual-context extraction path are integrated to boost the final counting result. Extensive experiments on vehicle counting and crowd counting datasets including TRANCOS, Mall, Shanghaitech_A and WorldExpo’10 demonstrate the feasibility and effectiveness for the object counting task.

Ultra-long-term subcutaneous home monitoring of epilepsy-490days of EEG from nine patients.

ObjectiveTo explore the feasibility of home monitoring of epilepsy patients with a novel subcutaneous electroencephalography (EEG) device, including clinical implications, safety, and compliance via the first real‐life test.MethodsWe implanted a beta‐version of the 24/7 EEG SubQ (UNEEG Medical A/S, Denmark) subcutaneously in nine participants with temporal lobe epilepsy. Data on seizures, adverse events, compliance in using the device, and use of antiepileptic drugs (AEDs) were collected. EEG was recorded for up to 3 months, and all EEG data were reviewed visually to identify electrographic seizures. These were descriptively compared to seizure counts and AED changes reported in diaries from the same period.ResultsFour hundred ninety days of EEG and 338 electrographic seizures were collected. Eight participants completed at least 9 weeks of home monitoring, while one cancelled participation after 4 weeks due to postimplantation soreness. In total, 13 cases of device‐related adverse events were registered, none of them serious. Recordings obtained from the device covered 73% of the time, on average (range 45%‐91%). Descriptively, electrographic seizure counts were substantially different from diary seizure counts. We uncovered several cases of underreporting and revealed important information on AED response. Electrographic seizure counts revealed circadian distributions of seizures not visible from seizure diaries.SignificanceThe study shows that home monitoring for up to 3 months with a subcutaneous EEG device is feasible and well tolerated. No serious adverse device‐related events were reported. An objective seizure count can be derived, which often differs substantially from self‐reported seizure counts. Larger clinical trials quantifying the benefits of objective seizure counting should be a priority for future research as well as development of algorithms for automated review of data.

Voxel transformation: scalable scene geometry discretization for global illumination

In real-time computer graphics, efficient discretization of scenes is required in order to accelerate graphics related algorithms such as realistic rendering with indirect illumination and visibility checking. Sparse voxel octree (SVO) is a popular data structure for such a discretization task. Populating an SVO with data is challenging when dynamic object count is high, especially when data per spatial location is large. Problem of populating such trees is adressed with our Voxel Transformation method, where pre-generated voxel data is transformed from model space to world space on demand, in contrast to the common way of voxelizing each dynamic object over each frame. Additionally, an accompanying filtering technique for voxel transformation is also proposed. This technique serves proposed system in two ways: (1) resolves issues introduced by the proposed fast and scalable voxel transformation method, and (2) enables smooth transitions between frames and handles the aliasing problem naturally as shown in the supplementary video. As an application use case, the proposed Voxel Transformation method is demonstrated in order to achieve indirect illumination using the well-known voxel cone tracing method. Results, which is compared with the standard voxelization method and ground-truth, are visually appealing and also scalable over large number of dynamic objects as shown in the supplementary video.

Counting Objects by Blockwise Classification

In this paper, we introduce the idea of blockwise classification to count objects. The current mainstream method for counting objects is to regress the density map or to regress the redundant count map via a deep convolutional neural network (CNN). However, these methods suffer from two critical issues: inaccurately generated regression targets and serious sample imbalances. First, the ground truth density map is generated by convolving the dot map using a Gaussian kernel. Because an inappropriate kernel can cover the background or uncover objects, this approach introduces a form of noise, and therefore results in ambiguities when training the networks. Second, inhomogeneously distributed objects often exist in images, which gives rise to a data collection bias. This leads to a long-tailed distribution of region counts, which is a typical characteristic that occurs with imbalanced samples; therefore, underestimations in high-density regions and overestimations in low-density regions are common. In this paper, we address these two issues within one framework—blockwise count level classification. The intuition behind this idea is that while it may not be possible to provide an exact count of pixels or patches, it is possible to provide a count of a region that falls within a certain interval with high confidence. Our method classifies the count levels of each block produced by nonlinearly quantizing the continuous counts, thus transforming the imbalance of sample patch counts into a class imbalance of count levels. Consequently, an information-entropy-inspired loss can be applied to alleviate this issue. Through ablative studies, we analyze the impact of imbalanced data, Gaussian kernel sizes, quantization errors, and the effectiveness of each module in our method. Without bells and whistles, our method outperforms or performs competitively with other state-of-the-art approaches on seven object-counting benchmarks, including four crowd-counting datasets from ShanghaiTech, WorldExpo’10, UCF-QNRF and UCF_CC_50, one vehicle-counting dataset (TRANCOS), one maize-tassel-counting dataset (MTC), and one challenging sonar fish-counting dataset that we constructed. The results suggest that our framework provides a strong and improved baseline for object counting.

Microstructure affects light scattering in apples

The success of long-term storage of apples under controlled atmosphere (CA) depends, amongst others, on the gas exchange properties of the fruit. As gas exchange is effectively dictated by the microstructure of the fruit, the ability to obtain microstructure data becomes critical to improve storage solutions. The current study complements scattering measurements by means of spatially resolved spectroscopy (SRS) with 3D microstructure data obtained with contrast enhanced X-ray computed micro-tomography (micro-CT). Complementary measurements with both techniques were performed on apples of different cultivars that have different optimal storage conditions and different fleshy microstructure (‘Kanzi’, ‘Braeburn’, ‘Jonagold’ and ‘Golden Delicious’). The mean reduced scattering coefficients of the subsurface tissue were calculated from SRS measurements in the 750 nm to 900 nm range at specific equatorial positions on the intact apple. Microstructural parameters such as cell size (equivalent spherical diameter), anisotropy, elongation, flatness, sphericity, object count, porosity as well as pore surface density were quantified and analyzed at the same spot up to 3 mm in depth from the fruit surface. A partial least squares regression model using the microstructural parameters as the different variables to predict the reduced scattering coefficient was built in order to identify the parameters contributing most to this relation. Both mean porosity and pore surface density showed the largest absolute regression coefficients. Furthermore, plotting the reduced scattering coefficient against mean porosity and pore surface density produced a linear relationship between the two parameters with an R2 of 0.89 for both sets of data. The linear relationship suggests that the porosity of individual fruit can be determined via optical SRS measurements. This could allow to sort fruit based on their porosity, thus promoting fine tuning of the storage strategies by reducing variation in the porosity and gas exchange rate of the fruit being stored together.

Towards pixel-to-pixel deep nucleus detection in microscopy images

BackgroundNucleus or cell detection is a fundamental task in microscopy image analysis and supports many other quantitative studies such as object counting, segmentation, tracking, etc. Deep neural networks are emerging as a powerful tool for biomedical image computing; in particular, convolutional neural networks have been widely applied to nucleus/cell detection in microscopy images. However, almost all models are tailored for specific datasets and their applicability to other microscopy image data remains unknown. Some existing studies casually learn and evaluate deep neural networks on multiple microscopy datasets, but there are still several critical, open questions to be addressed.ResultsWe analyze the applicability of deep models specifically for nucleus detection across a wide variety of microscopy image data. More specifically, we present a fully convolutional network-based regression model and extensively evaluate it on large-scale digital pathology and microscopy image datasets, which consist of 23 organs (or cancer diseases) and come from multiple institutions. We demonstrate that for a specific target dataset, training with images from the same types of organs might be usually necessary for nucleus detection. Although the images can be visually similar due to the same staining technique and imaging protocol, deep models learned with images from different organs might not deliver desirable results and would require model fine-tuning to be on a par with those trained with target data. We also observe that training with a mixture of target and other/non-target data does not always mean a higher accuracy of nucleus detection, and it might require proper data manipulation during model training to achieve good performance.ConclusionsWe conduct a systematic case study on deep models for nucleus detection in a wide variety of microscopy images, aiming to address several important but previously understudied questions. We present and extensively evaluate an end-to-end, pixel-to-pixel fully convolutional regression network and report a few significant findings, some of which might have not been reported in previous studies. The model performance analysis and observations would be helpful to nucleus detection in microscopy images.

Beyond counting: point supervised attention guided neural network for crowded object locating

Recent advances in convolutional neural networks have achieved prominent results for object counting or locating in images. In these networks, some adopt detection-based methods which require providing bounding-box annotations for training and these methods usually cannot deal with the crowded cases well. Other networks adopt density regression-based methods which require only point annotations for training but these methods can only predict the total count without providing any location information. In this Letter, the authors propose an attention guided convolutional neural network (AGNet) for both crowded object locating and counting using point annotation as supervision without annotated bounding boxes which are far more time-consuming to label. Accordingly, they define a multi-task objective loss function to lead the training of AGNet to achieve the goal of crowded object locating. The experimental results on four challenging benchmark datasets for crowded objects counting demonstrate the superiority of the proposed AGNet over recent state-of-the-art approaches.

Using Herschel and Planck observations to delineate the role of magnetic fields in molecular cloud structure

We present a study of the relative orientation between the magnetic field projected onto the plane of sky (B⊥) on scales down to 0.4 pc, inferred from the polarized thermal emission of Galactic dust observed by Planck at 353 GHz, and the distribution of gas column density (NH) structures on scales down to 0.026 pc, derived from the observations by Herschel in submillimeter wavelengths, toward ten nearby (d < 450 pc) molecular clouds. Using the histogram of relative orientation technique in combination with tools from circular statistics, we found that the mean relative orientation between NH and B⊥ toward these regions increases progressively from 0°, where the NH structures lie mostly parallel to B⊥, with increasing NH, in many cases reaching 90°, where the NH structures lie mostly perpendicular to B⊥. We also compared the relative orientation between NH and B⊥ and the distribution of NH, which is characterized by the slope of the tail of the NH probability density functions (PDFs). We found that the slopes of the NH PDF tail are steepest in regions where NH and B⊥ are close to perpendicular. This coupling between the NH distribution and the magnetic field suggests that the magnetic fields play a significant role in structuring the interstellar medium in and around molecular clouds. However, we found no evident correlation between the star formation rates, estimated from the counts of young stellar objects, and the relative orientation between NH and B⊥ in these regions.

Adaptive Communication for Battery-Free Devices in Smart Homes

With the ever-growing usage of batteries in the IoT era, the need for more eco-friendly technologies is clear. RF-powered computing enables the redesign of personal computing devices in a battery-less manner. While there has been substantial work on the underlying methods for RF-powered computing, practical applications of this technology has largely been limited to scenarios that involve simple tasks. This paper demonstrates how RFID technology, typically used to implement object identification and counting, can be exploited to realize a battery-free smart home. In particular, we consider the coexistence of several battery-free devices, with different transmission requirements-periodic, event-based, and real-time-and propose a new adaptive and quick-to-learn MAC protocol, called APT-MAC, which dynamically collects information from devices without requiring any a priori knowledge of the environment. Extensive simulations clearly show the benefits of using APT-MAC, which is able to successfully deliver 97.7% of new data samples in complex scenarios, including several high traffic demanding devices, such as joysticks and cameras.

Determining Star Formation Thresholds from Observations

Abstract Most gas in giant molecular clouds is relatively low-density and forms star inefficiently, converting only a small fraction of its mass to stars per dynamical time. However, star formation models generally predict the existence of a threshold density above which the process is efficient and most mass collapses to stars on a dynamical timescale. A number of authors have proposed observational techniques to search for a threshold density above which star formation is efficient, but it is unclear which of these techniques, if any, are reliable. In this paper we use detailed simulations of turbulent, magnetised star-forming clouds, including stellar radiation and outflow feedback, to investigate whether it is possible to recover star formation thresholds using current observational techniques. Using mock observations of the simulations at realistic resolutions, we show that plots of projected star formation efficiency per free-fall time εff can detect the presence of a threshold, but that the resolutions typical of current dust emission or absorption surveys are insufficient to determine its value. In contrast, proposed alternative diagnostics based on a change in the slope of the gas surface density versus star formation rate surface density (Kennicutt-Schmidt relation) or on the correlation between young stellar object counts and gas mass as a function of density are ineffective at detecting thresholds even when they are present. The signatures in these diagnostics sometimes taken as indicative of a threshold in observations, which we generally reproduce in our mock observations, do not prove to correspond to real physical features in the 3D gas distribution.

COMBImage2: a parallel computational framework for higher-order drug combination analysis that includes automated plate design, matched filter based object counting and temporal data mining

BackgroundPharmacological treatment of complex diseases using more than two drugs is commonplace in the clinic due to better efficacy, decreased toxicity and reduced risk for developing resistance. However, many of these higher-order treatments have not undergone any detailed preceding in vitro evaluation that could support their therapeutic potential and reveal disease related insights. Despite the increased medical need for discovery and development of higher-order drug combinations, very few reports from systematic large-scale studies along this direction exist. A major reason is lack of computational tools that enable automated design and analysis of exhaustive drug combination experiments, where all possible subsets among a panel of pre-selected drugs have to be evaluated.ResultsMotivated by this, we developed COMBImage2, a parallel computational framework for higher-order drug combination analysis. COMBImage2 goes far beyond its predecessor COMBImage in many different ways. In particular, it offers automated 384-well plate design, as well as quality control that involves resampling statistics and inter-plate analyses. Moreover, it is equipped with a generic matched filter based object counting method that is currently designed for apoptotic-like cells. Furthermore, apart from higher-order synergy analyses, COMBImage2 introduces a novel data mining approach for identifying interesting temporal response patterns and disentangling higher- from lower- and single-drug effects.COMBImage2 was employed in the context of a small pilot study focused on the CUSP9v4 protocol, which is currently used in the clinic for treatment of recurrent glioblastoma. For the first time, all 246 possible combinations of order 4 or lower of the 9 single drugs consisting the CUSP9v4 cocktail, were evaluated on an in vitro clonal culture of glioma initiating cells.ConclusionsCOMBImage2 is able to automatically design and robustly analyze exhaustive and in general higher-order drug combination experiments. Such a versatile video microscopy oriented framework is likely to enable, guide and accelerate systematic large-scale drug combination studies not only for cancer but also other diseases.