Enhancement of Construction Equipment Detection in Video Frames by Combining with Tracking

Vision-based object detection has been introduced in construction for recognizing and locating construction entities in on-site camera views. It can provide spatial locations of a large number of entities, which is beneficial in large-scale, congested construction sites. However, even a few false detections prevent its practical applications. In resolving this issue, this paper presents a novel hybrid method for locating construction equipment that fuses the function of detection and tracking algorithms. This method detects construction equipment in the video view by taking advantage of entities' motion, shape, and color distribution. Background subtraction, Haar-like features, and eigen-images are used for motion, shape, and color information, respectively. A tracking algorithm steps in the process to make up for the false detections. False detections are identified by catching drastic changes in object size and appearance. The identified false detections are replaced with tracking results. Preliminary experiments show that the combination with tracking has the potential to enhance the detection performance.

No evidence for an item limit in change detection.

Change detection is a classic paradigm that has been used for decades to argue that working memory can hold no more than a fixed number of items ("item-limit models"). Recent findings force us to consider the alternative view that working memory is limited by the precision in stimulus encoding, with mean precision decreasing with increasing set size ("continuous-resource models"). Most previous studies that used the change detection paradigm have ignored effects of limited encoding precision by using highly discriminable stimuli and only large changes. We conducted two change detection experiments (orientation and color) in which change magnitudes were drawn from a wide range, including small changes. In a rigorous comparison of five models, we found no evidence of an item limit. Instead, human change detection performance was best explained by a continuous-resource model in which encoding precision is variable across items and trials even at a given set size. This model accounts for comparison errors in a principled, probabilistic manner. Our findings sharply challenge the theoretical basis for most neural studies of working memory capacity.

Detection reliability analysis of passive DAS RFID system

Recently, it has been shown that improved wireless communication coverage can be achieved by employing distributed antenna system (DAS). The DAS RFID system is based on a novel technique whereby two or more spatially separated transmit and receive antennas are used to enable greatly enhanced tag detection performance over longer distances using antenna diversity combined with frequency and phase hopping. In this paper, we present a detection reliability evaluation of the DAS RFID in a typical lab environment. We conduct an extensive experimental analysis of passive RFID tag detection with different locations and orientations. The tag received signal strengths corresponding to various tag locations on one of the six different sides of a cube, and for different reader transmit power are collected and analyzed in this study.

Wide Area Passive UHF RFID System using Antenna Diversity Combined with Phase and Frequency Hopping

This paper presents a long range and effectively error-free ultra high frequency (UHF) radio frequency identification (RFID) interrogation system. The system is based on a novel technique whereby two or more spatially separated transmit and receive antennas are used to enable greatly enhanced tag detection performance over longer distances using antenna diversity combined with frequency and phase hopping. The novel technique is first theoretically modelled using a Rician fading channel. It is shown that conventional RFID systems suffer from multi-path fading resulting in nulls in radio environments. We, for the first time, demonstrate that the nulls can be moved around by varying the phase and frequency of the interrogation signals in a multi-antenna system. As a result, much enhanced coverage can be achieved. A proof of principle prototype RFID system is built based on an Impinj R2000 transceiver. The demonstrator system shows that the new approach improves the tag detection accuracy from <50% to 100% and the tag backscatter signal strength by 10dB over a 20 m x 9 m area, compared with a conventional switched multi-antenna RFID system.

The cross-entropy method for blind multiuser detection

We consider the problem of blind multiuser detection. We adopt a Bayesian approach where unknown parameters are considered random and integrated out. Computing the maximum a posteriori estimate of the input data sequence requires solving a combinatorial optimization problem. We propose here to apply the Cross-Entropy method recently introduced by Rubinstein. The performance of cross-entropy is compared to Markov chain Monte Carlo. For similar Bit Error Rate performance, we demonstrate that Cross-Entropy outperforms a generic Markov chain Monte Carlo method in terms of operation time.

PARTIALLY COHERENT DYNAMIC PROGRAMMING ALGORITHM FOR CPM DETECTION.

A dynamic programming algorithm for joint data detection and carrier phase estimation of continuous-phase-modulated signal is presented. The intent is to combine the robustness of noncoherent detectors with the superior performance of coherent ones. The algorithm differs from the Viterbi algorithm only in the metric that it maximizes over the possible transmitted data sequences. This metric is influenced both by the correlation with the received signal and the current estimate of the carrier phase. Carrier-phase estimation is based on decision guiding, but there is no external phase-locked loop. Instead, the phase of the best complex correlation with the received signal over the last few signaling intervals is used. The algorithm is slightly more complex than the coherent Viterbi algorithm but does not require narrowband filtering of the recovered carrier, as earlier appproaches did, to achieve the same level of performance.

Co-occurrence flow for pedestrian detection

The last few years have seen considerable progress in pedestrian detection. Recent work has established a combination of oriented gradients and optic flow as effective features although the detection rates are still unsatisfactory for practical use. This paper introduces a new type of motion feature, the co-occurrence flow (CoF). The advance is to capture relative movements of different parts of the entire body, unlike existing motion features which extract internal motion in a local fashion. Through evaluations on the TUD-Brussels pedestrian dataset, we show that our motion feature based on co-occurrence flow contributes to boost the performance of existing methods. © 2011 IEEE.

Defects Detection and Assessment in Concrete Surfaces

Aside from cracks, the impact of other surface defects, such as air pockets and discoloration, can be detrimental to the quality of concrete in terms of strength, appearance and durability. For this reason, local and national codes provide standards for quantifying the quality impact of these concrete surface defects and owners plan for regular visual inspections to monitor surface conditions. However, manual visual inspection of concrete surfaces is a qualitative (and subjective) process with often unreliable results due to its reliance on inspectors’ own criteria and experience. Also, it is labor intensive and time-consuming. This paper presents a novel, automated concrete surface defects detection and assessment approach that addresses these issues by automatically quantifying the extent of surface deterioration. According to this approach, images of the surface shot from a certain angle/distance can be used to automatically detect the number and size of surface air pockets, and the degree of surface discoloration. The proposed method uses histogram equalization and filtering to extract such defects and identify their properties (e.g. size, shape, location). These properties are used to quantify the degree of impact on the concrete surface quality and provide a numerical tool to help inspectors accurately evaluate concrete surfaces. The method has been implemented in C++ and results that validate its performance are presented.

Optimized vertical carbon nanotube forests for multiplex surface-enhanced raman scattering detection

The highly sensitive and molecule-specific technique of surface-enhanced Raman spectroscopy (SERS) generates high signal enhancements via localized optical fields on nanoscale metallic materials, which can be tuned by manipulation of the surface roughness and architecture on the submicrometer level. We investigate gold-functionalized vertically aligned carbon nanotube forests (VACNTs) as low-cost straightforward SERS nanoplatforms. We find that their SERS enhancements depend on their diameter and density, which are systematically optimized for their performance. Modeling of the VACNT-based SERS substrates confirms consistent dependence on structural parameters as observed experimentally. The created nanostructures span over large substrate areas, are readily configurable, and yield uniform and reproducible SERS enhancement factors. Further fabricated micropatterned VACNTs platforms are shown to deliver multiplexed SERS detection. The unique properties of CNTs, which can be synergistically utilized in VACNT-based substrates and patterned arrays, can thus provide new generation platforms for SERS detection. © 2012 American Chemical Society.

A performance evaluation of volumetric 3D interest point detectors

This paper presents the first performance evaluation of interest points on scalar volumetric data. Such data encodes 3D shape, a fundamental property of objects. The use of another such property, texture (i.e. 2D surface colouration), or appearance, for object detection, recognition and registration has been well studied; 3D shape less so. However, the increasing prevalence of 3D shape acquisition techniques and the diminishing returns to be had from appearance alone have seen a surge in 3D shape-based methods. In this work, we investigate the performance of several state of the art interest points detectors in volumetric data, in terms of repeatability, number and nature of interest points. Such methods form the first step in many shape-based applications. Our detailed comparison, with both quantitative and qualitative measures on synthetic and real 3D data, both point-based and volumetric, aids readers in selecting a method suitable for their application. © 2012 Springer Science+Business Media, LLC.

SOI CMOS integrated zinc oxide nanowire for toluene detection

The paper reports on the in-situ growth of zinc oxide nanowires (ZnONWs) on a complementary metal oxide semiconductor (CMOS) substrate, and their performance as a sensing element for ppm (parts per million) levels of toluene vapour in 3000 ppm humid air. Zinc oxide NWs were grown using a low temperature (only 90°C) hydrothermal method. The ZnONWs were first characterised both electrically and through scanning electron microscopy. Then the response of the on-chip ZnONWs to different concentrations of toluene (400-2600ppm) was observed in air at 300°C. Finally, their gas sensitivity was determined and found to lie between 0.1% and 0.3% per ppm. © 2013 IEEE.

System combination and score normalization for spoken term detection

Spoken content in languages of emerging importance needs to be searchable to provide access to the underlying information. In this paper, we investigate the problem of extending data fusion methodologies from Information Retrieval for Spoken Term Detection on low-resource languages in the framework of the IARPA Babel program. We describe a number of alternative methods improving keyword search performance. We apply these methods to Cantonese, a language that presents some new issues in terms of reduced resources and shorter query lengths. First, we show score normalization methodology that improves in average by 20% keyword search performance. Second, we show that properly combining the outputs of diverse ASR systems performs 14% better than the best normalized ASR system. © 2013 IEEE.

Investigation of multilingual deep neural networks for spoken term detection

The development of high-performance speech processing systems for low-resource languages is a challenging area. One approach to address the lack of resources is to make use of data from multiple languages. A popular direction in recent years is to use bottleneck features, or hybrid systems, trained on multilingual data for speech-to-text (STT) systems. This paper presents an investigation into the application of these multilingual approaches to spoken term detection. Experiments were run using the IARPA Babel limited language pack corpora (∼10 hours/language) with 4 languages for initial multilingual system development and an additional held-out target language. STT gains achieved through using multilingual bottleneck features in a Tandem configuration are shown to also apply to keyword search (KWS). Further improvements in both STT and KWS were observed by incorporating language questions into the Tandem GMM-HMM decision trees for the training set languages. Adapted hybrid systems performed slightly worse on average than the adapted Tandem systems. A language independent acoustic model test on the target language showed that retraining or adapting of the acoustic models to the target language is currently minimally needed to achieve reasonable performance. © 2013 IEEE.

High performance bilayer-graphene Terahertz detectors

© 2014 AIP Publishing LLC. We report bilayer-graphene field effect transistors operating as Terahertz (THz) broadband photodetectors based on plasma-waves excitation. By employing wide-gate geometries or buried gate configurations, we achieve a responsivity ∼1.2 V/W (1.3 mA/W) and a noise equivalent power ∼2 × 10-9 W/√Hz in the 0.29-0.38 THz range, in photovoltage and photocurrent mode. The potential of this technology for scalability to higher frequencies and the development of flexible devices makes our approach competitive for a future generation of THz detection systems.