An efficient and robust system for multi-person event detection in real world indoor surveillance scenes

Due to the popularity of security cameras in public places, it is of interest to design an intelligent system that can efficiently detect events automatically. This paper proposes a novel algorithm for multi-person event detection. To ensure greater than real-time performance, features are extracted directly from compressed MPEG video. A novel histogram-based feature descriptor that captures the angles between extracted particle trajectories is proposed, which allows us to capture motion patterns of multi-person events in the video. To alleviate the need for fine-grained annotation, we propose the use of Labelled Latent Dirichlet Allocation, a “weakly supervised” method that allows the use of coarse temporal annotations which are much simpler to obtain. This novel system is able to run at approximately ten times real-time, while preserving state-of-theart detection performance for multi-person events on a 100-hour real-world surveillance dataset (TRECVid SED).

Characterisation of indoor air organic pollutants in Brisbane

The occurrence and levels of airborne polycyclic aromatic hydrocarbons and volatile organic compounds in selected non-industrial environments in Brisbane have been investigated as part of an integrated indoor air quality assessment program. The most abundant and most frequently encountered compounds include, nonanal, decanal, texanol, phenol, 2-ethyl-1-hexanol, ethanal, naphthalene, 2,6-tert-butyl-4-methyl-phenol (BHT), salicylaldehyde, toluene, hexanal, benzaldehyde, styrene, ethyl benzene, o-, m- and pxylenes, benzene, n-butanol, 1,2-propandiol, and n-butylacetate. Many of the 64 compounds usually included in the European Collaborative Action method of TVOC analysis were below detection limits in the samples analysed. In order to extract maximum amount of information from the data collected, multivariate data projection methods have been employed. The implications of the information extracted on source identification and exposure control are discussed.

A pilot study on the effect of indoor particle sources on indoor particle concentration in residential houses

Characterization of indoor particle sources from 14 residential houses in Brisbane, Australia, was performed. The approximation of PM2.5 and the submicrometre particle number concentrations were measured simultaneously for more than 48 h in the kitchen of all the houses by using a photometer (DustTrak) and a condensation particle counter (CPC), respectively. From the real time indoor particle concentration data and a diary of indoor activities, the indoor particle sources were identified. The study found that among the indoor activities recorded in this study, frying, grilling, stove use, toasting, cooking pizza, smoking, candle vaporizing eucalyptus oil and fan heater use, could elevate the indoor particle number concentration levels by more than five times. The indoor approximation of PM2.5 concentrations could be close to 90 times, 30 times and three times higher than the background levels during grilling, frying and smoking, respectively.

Indoor exposure to submicrometer particles and PM2.5 in residential houses in Brisbane, Australia

As part of a large study investigating indoor air in residential houses in Brisbane, Australia, the purpose of this work was to quantify indoor exposure to submicrometer particles and PM2.5 for the inhabitants of 14 houses. Particle concentrations were measured simultaneously for more than 48 hours in the kitchens of all the houses by using a condensation particle counter (CPC) and a photometer (DustTrak). The occupants of the houses were asked to fill in a diary, noting the time and duration of any activity occurring throughout the house during measurement, as well as their presence or absence from home. From the time series concentration data and the information about indoor activities, exposure to the inhabitants of the houses was calculated for the entire time they spent at home as well as during indoor activities resulting in particle generation. The results show that the highest median concentration level occurred during cooking periods for both particle number concentration (47.5´103 particles cm-3) and PM2.5 concentration (13.4 mg m-3). The highest residential exposure period was the sleeping period for both particle number exposure (31%) and PM2.5 exposure (45.6%). The percentage of the average residential particle exposure level in total 24h particle exposure level was approximating 70% for both particle number and PM2.5 exposure.

Relationship between indoor/outdoor concentrations of particles : a critical review

The relationship between indoor and outdoor concentration levels of particles in the absence and in the presence of indoor sources has been attracting an increasing level of attention. Understanding of the relationship and the mechanisms driving it, as well as the ability to quantify it, are of importance for assessment of source contribution, assessment of human exposure and for control and management of particles. It became particularly important to address this topic when evidence came from epidemiological studies on the close association between outdoor concentration levels of particles and health effects, yet with many studies showing that indoor concentrations could be significantly higher than those outdoors. This paper presents a summary of an extensive literature review on this topic conducted with an aim to identify general trends in relation to the I/O relationship emerging from studies conducted worldwide. The review considered separately a larger body of papers published on PM10, PM2.5, as well as the smaller database on particle number and number or volume size distribution. A specific focus of this paper is on naturally ventilated houses. The conclusion from the review is that despite the multiplicity of factors that play role in affecting the relationship, there are clear trends emerging in relation to the I/O relationship for particle mass concentration, enabling more general predictions to be made about the relationship. However, more research is still needed on particle number concentration and size distribution.

Pedestrians Effects on Indoor MIMO-OFDM Channel Capacity

Temporal variations caused by pedestrian movement can significantly affect the channel capacity of indoor MIMOOFDM wireless systems. This paper compares systematic measurements of MIMO-OFDM channel capacity in presence of pedestrians with predicted MIMO-OFDM channel capacity values using geometric optics-based ray tracing techniques. Capacity results are presented for a single room environment using 5.2 GHz with 2x2, 3x3 and 4x4 arrays as well as a 2.45 GHz narrowband 8x8 MIMO array. The analysis shows an increase of up to 2 b/s/Hz on instant channel capacity with up to 3 pedestrians. There is an increase of up to 1 b/s/Hz in the average capacity of the 4x4 MIMO-OFDM channel when the number of pedestrians goes from 1 to 3. Additionally, an increment of up to 2.5 b/s/Hz in MIMO-OFDM channel capacity was measured for a 4x4 array compared to a 2x2 array in presence of pedestrians. Channel capacity values derived from this analysis are important in terms of understanding the limitations and possibilities for MIMO-OFDM systems in indoor populated environments.

Effect of Pedestrian Movement on MIMO-OFDM Channel Capacity in an Indoor Environment

Effects of pedestrian movement on multiple-input multiple-output orthogonal frequency division multiplexing (MIMO-OFDM) channel capacity have been investigated using experiment and simulation. The experiment was conducted at 5.2 GHz by a MIMO-OFDM packet transmission demonstrator using four transmitters and four receivers built in-house. Geometric optics based ray tracing technique was used to simulate the experimental scenarios. Changes in the channel capacity dynamic range have been analysed for different number of pedestrian (0-3) and antennas (2-4). Measurement and simulation results show that the dynamic range increases with the number of pedestrian and the number of antennas on the transmitter and receiver array.