![xaircraft flight control system xaircraft flight control system](http://i.ytimg.com/vi/AiTk5r-4coc/maxresdefault.jpg)
We describe methods that work in any application, but are specifically motivated by infrastructure inspection, so we point out the connections of vision and control with this area. Therefore, in the first part of the paper, we survey general techniques for vision and control. Building on vision, advanced sensing and control methods are used to compensate for the performance and capability limitations. Nevertheless, the cameras are the richest data sources, so computer vision usually plays a central role in UAV automation. Color cameras are used, which are useful only in daytime and do not provide depth and scale information for the captured environment.
![xaircraft flight control system xaircraft flight control system](https://i.pinimg.com/originals/fe/12/b2/fe12b2649d1e2937ef7707bec4909d77.gif)
They still possess basic navigation units, such as inertial measurement units (IMU) and possibly Global Positioning System (GPS) modules, but the measurement accuracy is usually reduced. UAVs under $1500 use less expensive hardware, especially for sensing and processing units. While such platforms are sometimes also referred to as low-cost UAVs, we consider here significantly less expensive UAVs. Among small-scale UAVs, higher-cost platforms, such as the AscTec, Draganflyer and MikroKopter products, offer improved flight stability and advanced sensing units, such as laser rangefinders or thermal infrared cameras. More generally, inexpensive UAVs are accessible to civilian users and commercially attractive for companies, making them more likely to become widespread. While the specific limits on size, weight and cost are, of course, arbitrary to an extent, we are also motivated to select them by the railway inspection application we discuss in Section 6: since the UAVs are small they are unlikely to damage a train in the event of an unavoidable collision, and their low cost makes them easily replaceable. Examples for UAVs that fit these criteria are the Parrot AR.Drone, the Arducopter platforms or others presented in Section 4. We focus here on low-cost (under $1500), small-scale (diameter under 1 m) and lightweight (under 4 kg) UAVs that can be reliably used outdoors. Although the legal requirements are still quite restrictive, UAV applications are becoming widespread, from military usage to civil applications, such as aerial imaging or various inspection tasks. Unmanned vehicles, including UAVs, offer new perspectives for transportation and services. To select vision methods, we run a thorough set of experimental evaluations. Finally, as an example, we formulate two use-cases for railway inspection, a less explored application field, and illustrate the usage of the vision and control techniques reviewed by selecting appropriate ones to tackle these use-cases. We discuss applications, restricting our focus to the field of infrastructure inspection. We then list popular low-cost UAVs, selecting mainly quadrotors. We overview, among others, feature detection and tracking, optical flow and visual servoing, low-level stabilization and high-level planning methods. We also highlight the sensor suites used where this information is available. In this report, we survey vision and control methods that can be applied to low-cost UAVs, and we list some popular inexpensive platforms and application fields where they are useful. Low-cost platforms using inexpensive sensor payloads have been shown to provide satisfactory flight and navigation capabilities. Unmanned aerial vehicles (UAVs) have gained significant attention in recent years.