Visual crowd counting estimates the density of the crowd using deep learning models such as convolution neural networks (CNNs). The performance of the model heavily relies on the quality of the training data that constitutes crowd images. In harsh weather such as fog, dust, and low light conditions, the inference performance may severely degrade on the noisy and blur images. In this paper, we propose the use of Pix2Pix generative adversarial network (GAN) to first denoise the crowd images prior to passing them to the counting model. A Pix2Pix network is trained using synthetic noisy images generated from original crowd images and then the pretrained generator is then used in the inference engine to estimate the crowd density in unseen, noisy crowd images. The performance is tested on JHU-Crowd dataset to validate the significance of the proposed method particularly when high reliability and accuracy are required.

You might soon see DJI's drones flying in particularly rough conditions. DJI has unveiled the Matrice 30 (aka M30), an enterprise-class drone with IP55 dust and water resistance that lets it fly in heavy rain, strong wind and even icy situations. It can fly to altitudes as high as 22,965ft above sea level (with the right propellers) and survive temperatures between -4F and 122F, too. Even the included RC Plus controller can handle a downpour thanks to an IP54-rated body. The M30 can also fold with a button press.

Outdoor smart plugs are increasingly common, but Lutron thinks it has an easy way to stand out: make a plug that can endure the worst nature has to offer. It's introducing a Caseta Outdoor Smart Plug that's IP65-rated, or tough enough to survive heavy rain, snow and dust. You can turn on your patio lights at sunset (or other devices) even when the weather is brutal enough to keep you indoors. The plug can also survive temperature extremes between -4F and 140F, and it's billed as "sunproof." The plug will also work with just about any smart home ecosystem.