This paper presents to detect the faces in an image and locates the facial features in an image. The detection of the facial parts such as eyes, nose, mouth and face is an important task in this process. This system is used to recognize and detect the parts of the human facial factors in an image. The study involves the algorithm of Viola-Jones Cascade Object Detector which gives various combination of filters and methods to detect these facial expressions.

Facial parts detection using Viola Jones algorithm

People counting has many applications in smart buildings For example, adjusting HVAC systems based on the number of occupants in each room can save a significant amount of energy In addition, security and safety of the building can be managed by determining the number and location of occupants Different technologies and sensing platforms have proposed for accurate and efficient people counting However, these solutions are expensive, hard to deploy, or privacy invasive We investigate the possibility of placing an 8×8 IR array sensor at the doorways and counting the number of people inside rooms Our solution is real-time, inexpensive, privacy preserving with much less deployment constraints compared to its competitors The proposed solution deals with realistic and dynamic changes in the sensing environment by leveraging a combination of Otsus thresholding and modeling thermal noise distribution We evaluated our solution via several controlled and uncontrolled real-world environments The results show an average of 93% accuracy in estimating the number of occupants in rooms

Measuring People-Flow through Doorways Using Easy-to-Install IR Array Sensors

Occupancy estimation is an important primitive for a wide range of applications including building energy efficiency, safety, and security. In this paper, we explore the potential of using depth sensors to detect, estimate, identify, and track occupants in buildings. While depth sensors have been widely used for human detection and gesture recognition, computer vision algorithms are typically run on a powerful computer like XBOX or Intel R CoreTM i7 processor. In this work, we develop a prototype system called FORK using off-the-shelf components that performs the entire depth data processing on a cheaper and low power ARM processor in real-time. As ARM processors are extremely weak in running computer vision algorithms, FORK is designed to detect humans and track them in a very efficient way by leveraging a novel lightweight model based approach instead of traditional approaches based on histogram of oriented gradients (HOG) features. Unlike other camera based approaches, FORK is much less privacy invasive (even if the sensor is compromised). Based on a complete implementation, real-world deployment, and extensive evaluation at realistic scenarios, we observe that FORK achieves over 99% accuracy in real-time (4-9 FPS) in occupancy estimation.

Real-Time Fine Grained Occupancy Estimation Using Depth Sensors on ARM Embedded Platforms

Recent works on crowd counting mainly leverage Convolutional Neural Networks
(CNNs) to count by regressing density maps, and have achieved great progress.
In the density map, each person is represented by a Gaussian blob, and the
final count is obtained from the integration of the whole map. However, it is
difficult to accurately predict the density map on dense regions. A major issue
is that the density map on dense regions usually accumulate density values from
a number of nearby Gaussian blobs. This results in the open end and imbalance
of density values, and presents a long-tailed density value distribution. In
this paper, we aim to address this long-tailed distribution issue in the
density map. Specifically, we propose a simple yet effective Learning to Scale
(L2S) module, which automatically scales dense regions into reasonable density
levels. It dynamically separates the overlapped blobs, decomposes the
accumulated values in the ground-truth density map, and thus alleviates the
long-tailed distribution of density values, which helps the model to better
learn the density map. We also explore the effectiveness of L2S on the
distance-like map, which is another trend to count by localization and has
similar issues as density map regression. We introduce a customized dynamic
cross-entropy loss, significantly improving the localization-based model
optimization. Extensive experiments demonstrate that the proposed framework
termed \textit{AutoScale} consistently improves upon some state-of-the-art
methods in both regression and localization benchmarks on three dense datasets
and achieves very competitive performance on two sparse datasets. Furthermore,
AutoScale shows a noteworthy transferability under cross-dataset validation on
different datasets. Code is available at
https://github.com/dk-liang/AutoScale.git

AutoScale: Learning to Scale for Crowd Counting.

People counting systems are widely used in surveillance applications. In this paper, we present a solution to bidirectional people counting based on information provided by an overhead stereo system. Four fundamental aspects can be identified: the detection and tracking of human motion using an extended particle filter, the use of 3-D measurements in order to increase the system's robustness and a modified K-means algorithm to provide the number of hypotheses at each time, and, finally, trajectory generation to facilitate people counting in different directions. The proposed algorithm is designed to solve problems of occlusion, without counting objects such as shopping trolleys or bags. A processing ratio of around 30 frames/s is necessary in order to capture the real-time trajectory of people and obtain robust tracking results. We validated various test videos, achieving a hit rate between 95% and 99%, depending on the number of people crossing the counting area.

/pdf/tracking-people-motion-based-on-extended-condensation-4pv2cq177e.pdf

Tracking People Motion Based on Extended Condensation Algorithm

Vision-based people counting systems have wide potential applications including video surveillance and public resources management. Most works in the literature rely on moving object detection and tracking, assuming that all moving objects are people. In this paper, we present our people counting approach based on face detection, tracking and trajectory classification. While we have used a standard face detector, we achieve face tracking combining a new scale invariant Kalman filter with kernel based tracking algorithm. From each potential face trajectory an angle histogram of neighboring points is then extracted. Finally, an Earth Mover's Distance-based K-NN classification discriminates true face trajectories from the false ones. Experimented on a video dataset of more than 160 potential people trajectories, our approach displays an accuracy rate up to 93%.

Emmanuel Delleandrea

Papers

A People Counting System Based on Face Detection and Tracking in a Video